© 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. 3406
    Prev
    Next
    INDEX
    Explanations

    Mac Mini, transcript evaluation

    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
    omer
    -0.09
    PLATFORM
    -0.09
    èĴ¯
    -0.09
    èĪĮ头
    -0.08
    ulo
    -0.08
    èŀ³
    -0.08
    åĿIJ
    -0.08
    æķ´æķ´
    -0.08
    ä¿Ŀå®Ī
    -0.08
    ä¿Ŀä½ı
    -0.08
    POSITIVE LOGITS
     Åļw
    0.10
    pson
    0.10
    /pub
    0.10
    дÑĥм
    0.09
    OTES
    0.09
    æ¼ĵ
    0.09
    angler
    0.09
    бÑĥÑĢ
    0.09
    cle
    0.09
    bull
    0.09
    Activations Density 0.003%

    No Known Activations