© 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. 3774
    Prev
    Next
    INDEX
    Explanations

    glance or glimpse

    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
    ãģıãĤĮ
    -0.10
    rement
    -0.08
    nt
    -0.08
    æŃ¥æŃ¥
    -0.08
    åı¥è¯Ŀ
    -0.08
    posite
    -0.08
    ä¸Ģç§į
    -0.08
    onald
    -0.08
    teen
    -0.08
    _glob
    -0.08
    POSITIVE LOGITS
    ãģĤãĤĮ
    0.10
    çĤ¯
    0.10
    _CID
    0.10
    aries
    0.10
    åŃIJéĩĮ
    0.09
    ä¸Ģçľ¼
    0.09
    仪表
    0.09
    ous
    0.09
    หา
    0.09
    åĵĪå°Ķ
    0.09
    Activations Density 0.004%

    No Known Activations