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

    Neuronpedia

    APICircuit 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. 36360
    Prev
    Next
    INDEX
    Explanations

    Technical content

    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
    _>
    -0.07
    ()):
    -0.07
    _feats
    -0.07
    dra
    -0.07
     quat
    -0.07
    če
    -0.07
    /cat
    -0.06
     Reception
    -0.06
    .creator
    -0.06
    _menu
    -0.06
    POSITIVE LOGITS
    峪
    0.07
     zobowiąz
    0.07
    ﮬ
    0.07
    딛
    0.07
    ILL
    0.07
    onic
    0.07
    𪩘
    0.06
    ctions
    0.06
    宽敞
    0.06
    Gro
    0.06
    Activations Density 0.002%

    No Known Activations