© 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. 27157
    Prev
    Next
    INDEX
    Explanations

    sort out

    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
    çŁ³å¤´
    -0.10
    ä½Ľæ³ķ
    -0.09
    æ±²åıĸ
    -0.09
    оваÑĢ
    -0.09
    è©
    -0.09
    åķĥ
    -0.09
    说æĺ¯
    -0.09
    ä¸Ģå¹ķ
    -0.09
    æĵĺ
    -0.09
    ÑĮÑĤе
    -0.09
    POSITIVE LOGITS
    ä¼Ĭæĭī
    0.10
    åĽ¢
    0.08
    æĺ¶
    0.08
    纶
    0.08
    empl
    0.08
    istically
    0.08
    overn
    0.08
    ta
    0.08
    лаг
    0.08
    ilent
    0.08
    Activations Density 0.007%

    No Known Activations