© 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. 19011
    Prev
    Next
    INDEX
    Explanations

    gatefold, reduction, distribution arm, compressed away

    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
    .fn
    -0.10
    å¢Ł
    -0.10
    æĪIJåIJį
    -0.10
    upal
    -0.09
     Lar
    -0.08
    è¯ī
    -0.08
    骥
    -0.08
     Gör
    -0.08
    æ¡ij
    -0.08
     swinger
    -0.08
    POSITIVE LOGITS
    è£ķ
    0.08
    帷
    0.08
    .detect
    0.08
    é¢Ħå¤ĩ
    0.08
    icot
    0.08
    åĮħ
    0.08
    帽åŃIJ
    0.08
    è´§
    0.08
    atur
    0.08
     ident
    0.08
    Activations Density 0.095%

    No Known Activations