© 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. 6270
    Prev
    Next
    INDEX
    Explanations

    halfway through

    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
    缮çļĦ
    -0.10
    inho
    -0.09
    é«ĺä½į
    -0.09
    温馨æıIJ示
    -0.09
    çļĦ缮çļĦ
    -0.08
    onal
    -0.08
     overs
    -0.08
     memorandum
    -0.08
    flix
    -0.08
    çıł
    -0.08
    POSITIVE LOGITS
    追éĢIJ
    0.10
    peg
    0.09
    å±ķè§Ī
    0.09
    éĻĪåĪĹ
    0.09
    æ·Į
    0.09
    两åij¨
    0.09
    ernel
    0.09
    legation
    0.09
    å®ł
    0.09
    typename
    0.08
    Activations Density 0.002%

    No Known Activations