© 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. 40163
    Prev
    Next
    INDEX
    Explanations

    one of the more

    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
    è¹ļ
    -0.10
    åĨ³ä¸į
    -0.10
     Rae
    -0.10
    rip
    -0.10
    ç½ijéĢļ
    -0.10
    åĬĽè¿ĺæĺ¯
    -0.09
    rips
    -0.09
    æIJ
    -0.09
    è¾°
    -0.09
    getBody
    -0.09
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.09
    åģļæ³ķ
    0.09
    bull
    0.09
    erman
    0.09
    ä¸Ģ段æŶéĹ´
    0.08
    ment
    0.08
    æī¹å¤į
    0.08
    å°Ķ
    0.08
    åIJįåŃĹ
    0.08
     dozen
    0.08
    Activations Density 0.007%

    No Known Activations