© 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. 1678
    Prev
    Next
    INDEX
    Explanations

    stop or end

    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
    æī£
    -0.11
    cgi
    -0.09
    åĪłéĻ¤æĪIJåĬŁ
    -0.09
    iry
    -0.09
    ä¸įèĪį
    -0.09
    æİ¥åıĹäºĨ
    -0.08
    rons
    -0.08
    为é¦ĸ
    -0.08
    åıijå±ķéĺ¶æ®µ
    -0.08
    жи
    -0.08
    POSITIVE LOGITS
    åģľæŃ¢
    0.26
    æŃ¢
    0.22
    -stop
    0.20
     stop
    0.20
     пÑĢек
    0.19
    _stop
    0.19
    åĪ¶æŃ¢
    0.18
     stops
    0.18
     Stop
    0.18
    stop
    0.18
    Activations Density 0.065%

    No Known Activations