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. 43869
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     economic
    -0.07
     Salmon
    -0.07
    (angle
    -0.07
     ot
    -0.07
    JEXEC
    -0.07
    .Rect
    -0.07
    ogonal
    -0.07
     infant
    -0.06
     Emotional
    -0.06
     Sea
    -0.06
    POSITIVE LOGITS
    (blank
    0.08
    _salary
    0.07
     weighted
    0.07
     сов
    0.07
    ⠀⠀
    0.07
    credential
    0.07
    _wait
    0.06
     beating
    0.06
    bullet
    0.06
    verbosity
    0.06
    Activations Density 0.008%

    No Known Activations