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. 24277
    Prev
    Next
    INDEX
    Explanations

    legal issues, issues of fact

    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
     Crane
    -0.07
     vulnerable
    -0.07
    (QWidget
    -0.07
    /base
    -0.07
    \Http
    -0.07
     tắc
    -0.07
    (const
    -0.07
    .dispose
    -0.07
     restTemplate
    -0.07
    <any
    -0.07
    POSITIVE LOGITS
    бы
    0.07
     effet
    0.07
     Hình
    0.07
    -after
    0.07
     appears
    0.07
    細
    0.06
    изма
    0.06
    者は
    0.06
    _PHP
    0.06
     Barack
    0.06
    Activations Density 0.003%

    No Known Activations