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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6885
    Prev
    Next
    INDEX
    Explanations

    Microsoft documentation

    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
    崭
    -0.08
    婚姻
    -0.07
    .Act
    -0.07
     Pope
    -0.07
     Coaching
    -0.07
     Master
    -0.07
    税收
    -0.07
     Generated
    -0.06
    成長
    -0.06
    _drive
    -0.06
    POSITIVE LOGITS
     лид
    0.08
     cityName
    0.07
    isers
    0.07
    安心
    0.07
    regor
    0.07
    ましょう
    0.07
    rames
    0.07
    镫
    0.07
    狙
    0.07
    非常适合
    0.07
    Activations Density 0.001%

    No Known Activations