© 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. 34178
    Prev
    Next
    INDEX
    Explanations

    states and Canadian provinces

    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
    该æĿij
    -0.11
    éĻķ
    -0.09
    å¨Ł
    -0.09
    åħ¥å¸Ĥ
    -0.09
    æ¼±
    -0.09
    æļĿ
    -0.09
    inha
    -0.09
    æĿij级
    -0.08
    xin
    -0.08
    èIJ¥è¿IJ
    -0.08
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.12
    .internet
    0.10
    ç±į
    0.10
    åĩºçĶŁ
    0.09
    åĩĽ
    0.08
    unday
    0.08
    æŁŀ
    0.08
    vig
    0.08
    ifference
    0.08
    anness
    0.08
    Activations Density 0.216%

    No Known Activations