© 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. 26693
    Prev
    Next
    INDEX
    Explanations

    Secret Show, Secret Fashion

    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
    æ²Ķ
    -0.11
     Pros
    -0.09
    ATAB
    -0.09
    ç«ĭæ¡Ī
    -0.08
    çī¢åĽº
    -0.08
    ç¿»
    -0.08
    ä¸įå°½
    -0.08
    è°ı
    -0.08
    _REFERER
    -0.08
    æ½ľ
    -0.08
    POSITIVE LOGITS
    常æĢģ
    0.10
    Ĥ¬
    0.09
    棺
    0.09
    поÑĤ
    0.09
    ä¸ī代
    0.08
    磼
    0.08
    åľŃ
    0.08
    uzzi
    0.08
    .joda
    0.08
    è·¯åı£
    0.08
    Activations Density 0.002%

    No Known Activations