© 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. 51525
    Prev
    Next
    INDEX
    Explanations

    scores and record

    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
     Shirley
    -0.09
     Wor
    -0.08
    contr
    -0.08
    lette
    -0.08
    éªŀ
    -0.08
    ä¸įæĪIJ
    -0.08
    LC
    -0.08
    å¾ĢåIJİ
    -0.08
    è¿İæİ¥
    -0.08
    iggins
    -0.08
    POSITIVE LOGITS
    èĸ®
    0.09
     lạc
    0.09
    .appspot
    0.09
    éķ¿èĢģ
    0.08
    onica
    0.08
    é£ŀæī¬
    0.08
    aque
    0.08
    éģ®
    0.08
    _specs
    0.08
     mascot
    0.08
    Activations Density 0.030%

    No Known Activations