© 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. 60848
    Prev
    Next
    INDEX
    Explanations

    vampire, Red,adon, writer

    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
    æĶĴ
    -0.11
    çľģåĨħ
    -0.09
    ä¸Ńå°ıåŀĭ
    -0.09
    ç¿ķ
    -0.09
    éĽ¨æ°´
    -0.09
    å°½æĹ©
    -0.09
    Âł↵
    -0.09
    è´
    -0.09
    èĭ´
    -0.09
    Observers
    -0.08
    POSITIVE LOGITS
    å·´èı²çī¹
    0.10
    èĮħ
    0.09
    èĺ§
    0.08
    RF
    0.08
    át
    0.08
    ä¸įåİ»
    0.08
    ç®Ģ称
    0.08
    ç¼ļ
    0.08
     panda
    0.08
    åĽ½éĻħæľºåľº
    0.08
    Activations Density 0.537%

    No Known Activations