© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    location and concept phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    俨
    -0.09
    eldon
    -0.09
    agt
    -0.09
    uling
    -0.09
    è°¯
    -0.09
    宾
    -0.08
    åħ¥åħļ
    -0.08
    鲤
    -0.08
    ResponseStatus
    -0.08
    å¢Ļå£ģ
    -0.08
    POSITIVE LOGITS
    禹
    0.09
    对å¤ĸ
    0.09
    edor
    0.09
    mh
    0.09
    ths
    0.09
     flashback
    0.08
    asca
    0.08
    ãģĽãģĦ
    0.08
    RID
    0.08
     trek
    0.08
    Activations Density 0.085%

    No Known Activations