© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38404
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    etto
    -0.10
    ä½İ温
    -0.09
    htag
    -0.09
    quivo
    -0.09
    umper
    -0.09
     memo
    -0.09
    веÑģÑĤи
    -0.08
    legg
    -0.08
    .memo
    -0.08
     ConfigurationManager
    -0.08
    POSITIVE LOGITS
    ãģ«åŁºãģ¥
    0.12
    çŃīåĽłç´ł
    0.11
    ä¸ºåŁºç¡Ģ
    0.10
    Based
    0.10
     based
    0.09
    å®ŀéĻħæĥħåĨµ
    0.09
    æĭĪ
    0.09
    based
    0.09
    åĽłç´ł
    0.08
    è¿Ļ个æĹ¶ä»£
    0.08
    Activations Density 0.079%

    No Known Activations