© 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. 18042
    Prev
    Next
    INDEX
    Explanations

    following a list or set of items

    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
    èİł
    -0.09
    çļĦæľĢåIJİä¸Ģ
    -0.09
    çļĦåIJĦ项
    -0.09
    åĽŀ头
    -0.08
    .logging
    -0.08
    çݺ
    -0.08
    ipur
    -0.08
    includes
    -0.08
    uding
    -0.08
    èĪĤ
    -0.08
    POSITIVE LOGITS
    ä¸ĭéĿ¢
    0.11
    ä¸ĭåĪĹ
    0.10
     below
    0.10
    ä¹ĭä¸ĭ
    0.09
    对çħ§
    0.09
    以ä¸ĭãģ®
    0.09
    以ä¸ĭ
    0.09
    次ãģ®
    0.08
    ä¸Ģå°ģ
    0.08
    温æŁĶ
    0.08
    Activations Density 0.073%

    No Known Activations