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. 2636
    Prev
    Next
    INDEX
    Explanations

    span

    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
    .onActivityResult
    -0.07
    "indices
    -0.07
     uranus
    -0.07
    臉
    -0.07
    石油化工
    -0.07
     zIndex
    -0.07
     Xamarin
    -0.07
     specular
    -0.06
    即便
    -0.06
    重點
    -0.06
    POSITIVE LOGITS
    (distance
    0.07
     renewable
    0.07
    (proxy
    0.07
    检察院
    0.07
    /apimachinery
    0.07
    _street
    0.07
    ]'↵
    0.06
    MBED
    0.06
    osta
    0.06
     fon
    0.06
    Activations Density 0.001%

    No Known Activations