© 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. 32160
    Prev
    Next
    INDEX
    Explanations

    progresses to acute

    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
    åĿ¨
    -0.10
    chron
    -0.09
    æĤ£
    -0.09
     chù
    -0.09
    åįł
    -0.08
    èĤ¥
    -0.08
     Chronic
    -0.08
    .Serialize
    -0.08
    otch
    -0.08
    åħį
    -0.08
    POSITIVE LOGITS
    è¿ħéĢŁ
    0.13
    apid
    0.10
    ç«ĭåį³
    0.10
    çĮĽçĥĪ
    0.10
    æĹ¥è®¯
    0.09
    马ä¸Ĭ
    0.09
    ç´§æĢ¥
    0.09
    管å±Ģ
    0.09
    æĿ¥ä¸įåıĬ
    0.09
    èijµ
    0.09
    Activations Density 0.152%

    No Known Activations