© 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. 4215
    Prev
    Next
    INDEX
    Explanations

    during specific historical periods or conflicts

    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
    çľ¼åīįçļĦ
    -0.09
    åĩºè·¯
    -0.09
    ä¸Ģçľĭ
    -0.09
    建æĪIJåIJİ
    -0.09
    roc
    -0.09
    代价
    -0.08
    linger
    -0.08
    ç¿ħ
    -0.08
    æĭ¢
    -0.08
     Garmin
    -0.08
    POSITIVE LOGITS
    æĹ¶æľŁ
    0.11
    éĹ¹
    0.11
     Ble
    0.09
    çīł
    0.09
    äºijéĽĨ
    0.09
    /high
    0.09
    æĬĹåĩ»
    0.09
    æľ±
    0.09
    åŃļ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    Activations Density 0.056%

    No Known Activations