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. 88078
    Prev
    Next
    INDEX
    Explanations

    a or an

    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
    okes
    -0.09
    תוך
    -0.07
    'Neill
    -0.07
    valor
    -0.07
    涄
    -0.07
    ".$_
    -0.07
    Fa
    -0.07
    udeau
    -0.07
     furious
    -0.07
     cupcakes
    -0.07
    POSITIVE LOGITS
    ريب
    0.07
    >`↵
    0.07
    锂
    0.07
    ятия
    0.07
    xyz
    0.07
    的新
    0.07
    exchange
    0.07
    loops
    0.07
     (...)
    0.07
    _Post
    0.07
    Activations Density 0.074%

    No Known Activations