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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 71880
    Prev
    Next
    INDEX
    Explanations

    1

    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
    叫做
    -0.07
    全国人民
    -0.07
    صال
    -0.07
    .ScrollBars
    -0.06
     chosen
    -0.06
    极大的
    -0.06
    izzato
    -0.06
    حرية
    -0.06
     טיול
    -0.06
    POSITIVE LOGITS
     aggregates
    0.08
    (ok
    0.08
     craft
    0.08
     mist
    0.07
    .ul
    0.07
    .segments
    0.07
    /meta
    0.07
    _set
    0.07
    _AUT
    0.07
     пл
    0.07
    Activations Density 0.028%

    No Known Activations