© 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. 62299
    Prev
    Next
    INDEX
    Explanations

    software licensing agreements

    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
    onds
    -0.09
    inez
    -0.09
    undo
    -0.09
    CastException
    -0.09
    coli
    -0.09
    å£ij
    -0.09
    _into
    -0.09
     cầm
    -0.08
    çĥ¨
    -0.08
    èı©æıIJ
    -0.08
    POSITIVE LOGITS
    ao
    0.10
    工夫
    0.09
    laps
    0.09
    å¾Īæľī
    0.09
    ä¼Ĺ
    0.08
    åĬŁå¤«
    0.08
    ì§ģ
    0.08
    -th
    0.08
    å¾Ģäºĭ
    0.08
    æ²±
    0.08
    Activations Density 0.006%

    No Known Activations