© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 18404
    Prev
    Next
    INDEX
    Explanations

    ];

    np_max-act · gemini-2.0-flash

    nucleotide sequence patterns and codon blocks characteristic of FASTA/genomic data.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thro
    -0.07
    -bound
    -0.07
    .radioButton
    -0.06
    そして
    -0.06
    ạt
    -0.06
    cold
    -0.06
     PTR
    -0.06
    ထ
    -0.06
     current
    -0.06
    IRT
    -0.06
    POSITIVE LOGITS
    最基本的
    0.08
    _advanced
    0.07
     syscall
    0.07
    -sample
    0.07
    larına
    0.07
    בי
    0.07
    .Subscribe
    0.07
    新形势
    0.06
    四季
    0.06
     vivo
    0.06
    Activations Density 5.260%

    No Known Activations