© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36323
    Prev
    Next
    INDEX
    Explanations

    matte finishes

    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
    naire
    -0.12
    ondo
    -0.10
     ÑĢайона
    -0.09
    ĺ
    -0.09
    oping
    -0.09
    rm
    -0.09
    ÑıÑħ
    -0.09
    涯
    -0.08
     Nähe
    -0.08
    nal
    -0.08
    POSITIVE LOGITS
    anus
    0.09
    eenth
    0.09
    çĤī
    0.09
    工夫
    0.08
    è®°å¾Ĺ
    0.08
    ynn
    0.08
    æŁ³
    0.08
    OTE
    0.08
    åIJĦæľī
    0.08
    afil
    0.08
    Activations Density 0.024%

    No Known Activations