© 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. 31333
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by words

    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
    çĦ¶æĺ¯
    -0.11
    Ø¡
    -0.10
    TING
    -0.10
    kers
    -0.09
    arf
    -0.09
    æĢ§å¼º
    -0.09
    à¸ĺรรม
    -0.09
    ASSES
    -0.09
    idad
    -0.09
    ×Ļ×IJ
    -0.09
    POSITIVE LOGITS
    side
    0.10
    ãģĹãģ¾ãģĨ
    0.10
    ing
    0.10
    Â
    0.09
    ord
    0.09
    enticate
    0.09
    a
    0.09
    ors
    0.08
    es
    0.08
    s
    0.08
    Activations Density 0.055%

    No Known Activations