© 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. 17238
    Prev
    Next
    INDEX
    Explanations

    the HOUSTON

    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
    å¾ĹæĦı
    -0.10
    ç½ijç«Ļé¦ĸ页
    -0.10
    微信åı·
    -0.10
    åŃº
    -0.09
    outs
    -0.09
    娱
    -0.09
    å¤§åĽ½
    -0.09
    ASF
    -0.09
    åģļçļĦäºĭæĥħ
    -0.09
    еÑĤÑĮ
    -0.09
    POSITIVE LOGITS
    èį·
    0.09
     Challenger
    0.08
    جÙĦ
    0.08
    _CA
    0.07
     Hera
    0.07
    ullen
    0.07
     endangered
    0.07
    erial
    0.07
    ivers
    0.07
     suppressed
    0.07
    Activations Density 0.120%

    No Known Activations