Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71108
    Prev
    Next
    INDEX
    Explanations

    say "the"

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    signup
    -0.07
    튜
    -0.07
    愈发
    -0.07
    也是一种
    -0.07
     weaker
    -0.07
    iband
    -0.07
    Tech
    -0.07
    \base
    -0.06
    人生的
    -0.06
    贸
    -0.06
    POSITIVE LOGITS
     flooring
    0.07
     הנתבע
    0.07
    }&
    0.07
    /
    0.07
    셤
    0.07
    לק
    0.07
    遗忘
    0.07
    .She
    0.07
     Shelley
    0.06
    ければ
    0.06
    Activations Density 0.025%

    No Known Activations