© 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. 27181
    Prev
    Next
    INDEX
    Explanations

    headlines and news

    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
    est
    -0.10
    inha
    -0.09
    portun
    -0.09
    奥迪
    -0.08
     Minor
    -0.08
     Se
    -0.08
    车ä¸Ĭ
    -0.08
    e
    -0.07
     sail
    -0.07
    -
    -0.07
    POSITIVE LOGITS
     headlines
    0.15
    头æĿ¡
    0.13
    éģIJ
    0.12
    è´ŁéĿ¢
    0.11
    åªĴ
    0.11
     headline
    0.11
    æľĢå¤ļ
    0.10
    _NEG
    0.10
    éģķ
    0.10
    åĨįä¸Ģ次
    0.10
    Activations Density 0.028%

    No Known Activations