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. 87844
    Prev
    Next
    INDEX
    Explanations

    are

    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
    _Callback
    -0.07
     BoxFit
    -0.07
    萜
    -0.07
    -La
    -0.07
    clus
    -0.07
     rewarded
    -0.07
     Cộng
    -0.07
     xpos
    -0.07
    胛
    -0.07
     bậ
    -0.07
    POSITIVE LOGITS
     assortment
    0.08
    September
    0.07
    \"
    0.06
    角度
    0.06
    Yeah
    0.06
     הם
    0.06
    variant
    0.06
    KHR
    0.06
     performances
    0.06
    STR
    0.06
    Activations Density 0.020%

    No Known Activations