© 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. 9828
    Prev
    Next
    INDEX
    Explanations

    ecma International

    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
    _PE
    -0.09
    ë²Į
    -0.09
    sic
    -0.09
    ç»ĵæĻ¶
    -0.09
     Lust
    -0.09
    rir
    -0.09
    chor
    -0.09
    溥
    -0.08
    åįģ足
    -0.08
    iji
    -0.08
    POSITIVE LOGITS
    å°ĨåĨĽ
    0.10
    èĭ¦
    0.09
    ÙĥÙĪ
    0.09
    Ùĥ
    0.09
    kinson
    0.09
    à°ķ
    0.09
    èĢĥ
    0.09
    ikip
    0.09
    kt
    0.09
    kit
    0.09
    Activations Density 0.136%

    No Known Activations