© 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. 30293
    Prev
    Next
    INDEX
    Explanations

    paper crafting

    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
    åªļ
    -0.11
    åĭī
    -0.10
    åı¯æĥ³
    -0.10
    寮
    -0.09
    ä¸ĢåĪĨ
    -0.09
    å§Ķæīĺ
    -0.08
    ä¸ĢèĦļ
    -0.08
    ä¸Ģ项
    -0.08
    ä¸ŃåİŁ
    -0.08
    ä»Ĺ
    -0.08
    POSITIVE LOGITS
    çŃIJ
    0.09
    xsd
    0.09
    asc
    0.09
    åĨįéĢł
    0.09
    ardi
    0.09
     dr
    0.09
    _stdio
    0.09
    prene
    0.08
    大æĪĺ
    0.08
    æ¶Ŀ
    0.08
    Activations Density 0.012%

    No Known Activations