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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95233
    Prev
    Next
    INDEX
    Explanations

    .gms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    苻
    -0.07
     offseason
    -0.07
     juga
    -0.06
    olang
    -0.06
     Median
    -0.06
    平时
    -0.06
     STATS
    -0.06
    今
    -0.06
     fontSize
    -0.06
     คน
    -0.06
    POSITIVE LOGITS
    ރ
    0.07
    _tD
    0.07
    ips
    0.07
     Rak
    0.07
    част
    0.07
    ᓕ
    0.07
     Sz
    0.07
    滤
    0.07
    鲾
    0.07
     nueva
    0.06
    Activations Density 0.000%

    No Known Activations