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. 2732
    Prev
    Next
    INDEX
    Explanations

    say "to"

    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
    Malloc
    -0.08
    汋
    -0.08
    _runs
    -0.07
    พอ
    -0.07
    _jobs
    -0.07
    חוס
    -0.07
    iswa
    -0.07
     Incorrect
    -0.07
    _income
    -0.07
    izi
    -0.07
    POSITIVE LOGITS
    'utilisation
    0.07
     tailor
    0.07
     BF
    0.07
     Since
    0.07
    drawing
    0.07
     fst
    0.07
    应对
    0.07
    边际
    0.07
    billing
    0.06
    alogy
    0.06
    Activations Density 0.000%

    No Known Activations