© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9844
    Prev
    Next
    INDEX
    Explanations

    shaggy dog, tavis smiley, snoop

    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
    å¾ĴæŃ¥
    -0.09
    åīįä¸ī
    -0.08
    theses
    -0.08
    rades
    -0.08
    ANTE
    -0.08
    <!--[
    -0.08
    _above
    -0.08
    éĽģ
    -0.08
    ornado
    -0.08
    .createNew
    -0.08
    POSITIVE LOGITS
    å²ĺ
    0.10
    涯
    0.10
    ç¢ĵ
    0.10
    åѦåłĤ
    0.09
    ä¸Ģ次æĢ§
    0.09
    äºĭåIJİ
    0.09
    æĵĴ
    0.09
    away
    0.09
    adm
    0.08
     checkout
    0.08
    Activations Density 0.039%

    No Known Activations