© 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. 39671
    Prev
    Next
    INDEX
    Explanations

    in conjunction with

    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
    æĦŁè§īåĪ°
    -0.09
    æī¿åıĹ
    -0.09
    ä¸ĢåĪĩ
    -0.09
    没éĴ±
    -0.09
    ree
    -0.09
    身ä¸Ĭ
    -0.08
    æĴŃ
    -0.08
    atsu
    -0.08
    å¤Ħåľ¨
    -0.08
     yal
    -0.08
    POSITIVE LOGITS
    bred
    0.10
    å¾®ç¬ij
    0.09
    AIN
    0.09
    æ¸Ĭ
    0.09
    ä¸ºæľŁ
    0.08
    æĪĸå¤ļ
    0.08
    æı¡æīĭ
    0.08
    åĴĮå¹³
    0.08
    ä¸Ģåı£
    0.08
    åIJĮæł·çļĦ
    0.08
    Activations Density 0.079%

    No Known Activations