© 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. 64144
    Prev
    Next
    INDEX
    Explanations

    author of

    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
    _mC
    -0.11
    éĢŀ
    -0.10
    tings
    -0.10
    tures
    -0.10
    eam
    -0.09
    è¸ŀ
    -0.09
     Widow
    -0.09
    CRE
    -0.09
    ại
    -0.09
    管å§Ķä¼ļ
    -0.09
    POSITIVE LOGITS
    izations
    0.13
    enticator
    0.13
    itative
    0.12
    иÑĤеÑĤ
    0.12
    ship
    0.11
    elmet
    0.10
    ENTICATION
    0.10
    enticated
    0.10
    itarian
    0.10
    ing
    0.10
    Activations Density 0.049%

    No Known Activations