© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48003
    Prev
    Next
    INDEX
    Explanations

    close related terms

    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
    è¤Ĵ
    -0.09
     иÑģÑĤоÑĩ
    -0.09
    _accessor
    -0.09
    invisible
    -0.09
    íı´
    -0.08
    迷失
    -0.08
    plib
    -0.08
    åıijçĶµæľº
    -0.08
    /bootstrap
    -0.08
    imet
    -0.08
    POSITIVE LOGITS
    亲å¯Ĩ
    0.10
    Close
    0.10
    åļ¼
    0.10
    close
    0.10
     Close
    0.09
    rics
    0.09
    ÑģÑĤва
    0.09
     clos
    0.08
    edly
    0.08
    å¯ĨåĪĩ
    0.08
    Activations Density 0.019%

    No Known Activations