© 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. 21789
    Prev
    Next
    INDEX
    Explanations

    chigger, Khovanova, SyntaxHighlighter

    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
    clearfix
    -0.09
    å¼ķãģį
    -0.08
    oste
    -0.08
    ional
    -0.08
    è¾ŀ
    -0.08
    çĵ¯
    -0.08
     sÆ°
    -0.07
    _chat
    -0.07
    _Char
    -0.07
    åĥ§
    -0.07
    POSITIVE LOGITS
    acter
    0.11
    istry
    0.10
    讼
    0.10
    lain
    0.09
    çıº
    0.09
    vard
    0.09
    èĢģ人家
    0.09
    ingleton
    0.09
    饮水
    0.09
    稷
    0.09
    Activations Density 0.449%

    No Known Activations