© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9141
    Prev
    Next
    INDEX
    Explanations

    recognized as

    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
    å¼ĺæī¬
    -0.11
    家åĽŃ
    -0.09
    èĩªè´Ł
    -0.09
    对ä»ĸ们
    -0.09
    _processors
    -0.09
    è°ĥåij³
    -0.09
    çĥĪ
    -0.09
    æŁ¥çľĭ详æĥħ
    -0.09
    ä¸įä¹ı
    -0.08
    gun
    -0.08
    POSITIVE LOGITS
    æѤäºĭ
    0.09
    .aw
    0.08
     Welch
    0.08
    ken
    0.08
    iasm
    0.08
    è¢Ī
    0.08
    ฤ
    0.08
    -Smith
    0.08
    没åĬŀæ³ķ
    0.08
    WithString
    0.07
    Activations Density 0.016%

    No Known Activations