© 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. 40180
    Prev
    Next
    INDEX
    Explanations

    been in existence for

    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
    Bel
    -0.09
    æĭ¾
    -0.09
    _batches
    -0.09
    èŀŁ
    -0.09
    è¿ĻæŶåĢĻ
    -0.09
    缮åīį为æŃ¢
    -0.09
    Bu
    -0.09
    å±ĬæŶ
    -0.08
    ddl
    -0.08
    åĩºæĿ¥äºĨ
    -0.08
    POSITIVE LOGITS
    abouts
    0.09
    礼è²Į
    0.09
    åĢ¾æĸľ
    0.09
    ols
    0.09
    cept
    0.08
     zug
    0.08
    oval
    0.08
     trá»įng
    0.08
    第ä¸Ģ家
    0.08
    gest
    0.08
    Activations Density 0.034%

    No Known Activations