© 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. 27817
    Prev
    Next
    INDEX
    Explanations

    quick solutions

    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
    avra
    -0.10
     ØŃص
    -0.10
    eenth
    -0.10
    etz
    -0.09
    ilog
    -0.09
    icas
    -0.09
    igroup
    -0.09
     ØŃÙĪ
    -0.09
    .ReadOnly
    -0.09
    undi
    -0.09
    POSITIVE LOGITS
     quick
    0.15
    Quick
    0.14
     Quick
    0.13
    å¿«éĢŁ
    0.12
    quick
    0.12
    è¿ħéĢŁ
    0.12
     quickly
    0.12
     QUICK
    0.11
    _quick
    0.11
    .quick
    0.10
    Activations Density 0.045%

    No Known Activations