© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29440
    Prev
    Next
    INDEX
    Explanations

    amount

    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
    Negative Logits
    bie
    -0.10
    常å§Ķ
    -0.10
     minded
    -0.09
    éļIJçŀĴ
    -0.09
    ammed
    -0.09
    cie
    -0.09
    åĬŁå¤«
    -0.09
    ẩm
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    born
    -0.09
    POSITIVE LOGITS
    èĥ¤
    0.09
    ingly
    0.09
    ing
    0.09
    ãĤ¥
    0.08
    оÑī
    0.08
    ials
    0.08
    æĻģ
    0.08
    oller
    0.08
    ullen
    0.08
    æ»ĭ
    0.08
    Activations Density 0.020%

    No Known Activations