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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23-RESID-POST-AA
    11. 600
    Prev
    Next
    INDEX
    Explanations

    Statistics in scientific studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .You
    -0.07
    .nlm
    -0.07
    ylabel
    -0.07
    .label
    -0.07
    宛
    -0.07
    sub
    -0.07
    ]
↵
    -0.07
     �
    -0.06
     authToken
    -0.06
    arus
    -0.06
    POSITIVE LOGITS
     evaluations
    0.08
     referrals
    0.07
     deliveries
    0.07
    _categories
    0.07
    เครด
    0.07
     cocktail
    0.07
    _TE
    0.07
     Investments
    0.07
     cumshot
    0.07
     teenage
    0.07
    Activations Density 0.141%

    No Known Activations