© 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. 27505
    Prev
    Next
    INDEX
    Explanations

    filler words and pauses

    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
    rian
    -0.09
    ATES
    -0.09
     Bod
    -0.09
    бÑĭ
    -0.09
    çĻ½é©¬
    -0.08
    _cached
    -0.08
    iband
    -0.08
    enson
    -0.08
    å°±è¦ģ
    -0.08
    ssi
    -0.08
    POSITIVE LOGITS
    åĵģè´¨
    0.11
    åĮĸè¿Ľç¨ĭ
    0.10
    èĢĮè¨Ģ
    0.09
    thur
    0.09
    åīįæīĢ
    0.09
    æģ¯æģ¯
    0.09
    请æĤ¨
    0.09
    éŁŃ
    0.08
    è´¢
    0.08
    財
    0.08
    Activations Density 0.039%

    No Known Activations