© 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. 16923
    Prev
    Next
    INDEX
    Explanations

    extortion, money, sharks

    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
    åıĽ
    -0.10
    å¼¢
    -0.10
    æī¿è½½
    -0.10
    ä¿¡æģ¯åıijå¸ĥ
    -0.10
    MEA
    -0.10
    å¤įåıij
    -0.09
     вли
    -0.09
    URLException
    -0.09
     Exc
    -0.09
    ðŁļ
    -0.09
    POSITIVE LOGITS
    åī¥
    0.11
    为é¦ĸ
    0.11
    èĭĽ
    0.10
    çĭł
    0.10
    秣
    0.10
    åĬłåĢį
    0.10
    åĪ°ä½į
    0.09
    åī¥å¤º
    0.09
    èµĦæľ¬ä¸»ä¹ī
    0.08
    æĤŃ
    0.08
    Activations Density 0.036%

    No Known Activations