© 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. 1561
    Prev
    Next
    INDEX
    Explanations

    kick up

    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
    ä¸ĭæĿ¥çļĦ
    -0.12
    å¾Ģ
    -0.10
    ä¸ĭåİ»
    -0.10
    çĢij
    -0.10
     Downs
    -0.10
    ä¼İ
    -0.10
    äºĨä¸ĭæĿ¥
    -0.10
    è¡£
    -0.10
    åĿļ飧
    -0.09
     trailing
    -0.09
    POSITIVE LOGITS
    ç¦Ħ
    0.10
    常æĢģ
    0.10
    unic
    0.08
    æĭ¾
    0.08
    LOOP
    0.08
    uchen
    0.08
     MSG
    0.07
    .sn
    0.07
    æļĤæŶ
    0.07
    æĬ¬
    0.07
    Activations Density 0.021%

    No Known Activations