© 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. 58332
    Prev
    Next
    INDEX
    Explanations

    just or only

    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
    æŀģ端
    -0.10
    æİĤ
    -0.09
    鼷éľĨ
    -0.09
    BYTE
    -0.09
    ä¹Łå°±æĺ¯
    -0.09
    çĸĥ
    -0.08
    åIJįèªī
    -0.08
    лиÑĤ
    -0.08
     coma
    -0.08
    _each
    -0.08
    POSITIVE LOGITS
     unt
    0.09
    éĻįèĩ³
    0.08
    hone
    0.08
     ones
    0.08
    ä¸İåIJ¦
    0.08
     Wholesale
    0.08
    ä¸Ģæ³¢
    0.08
    æĶ¾åģĩ
    0.08
     Clash
    0.08
    ANC
    0.08
    Activations Density 0.014%

    No Known Activations