© 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. 27039
    Prev
    Next
    INDEX
    Explanations

    start of phrases/clauses

    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
    ä¸ļ
    -0.10
    è®Ń
    -0.09
    éĽī
    -0.08
    æŁĺ
    -0.08
    大桥
    -0.08
    åIJİèĢħ
    -0.08
    rema
    -0.08
    à¸ģระà¸Ĺ
    -0.08
    ç»Ŀ
    -0.08
    壮大
    -0.08
    POSITIVE LOGITS
    çĭ¸
    0.11
    /generated
    0.09
    eling
    0.09
    ç¢İçīĩ
    0.09
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.09
    productName
    0.09
    èĥİ
    0.09
    isas
    0.08
    /cop
    0.08
    ocos
    0.08
    Activations Density 0.231%

    No Known Activations