© 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. 33834
    Prev
    Next
    INDEX
    Explanations

    legal or prohibited actions

    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
    æĹłæķ°
    -0.09
    ä¸ĢäºĽ
    -0.09
    çļĦä¸ĢäºĽ
    -0.09
    .inline
    -0.08
    åħ¬å®īéĥ¨
    -0.08
    OUS
    -0.08
    æ°´åĪĨ
    -0.08
     sometimes
    -0.08
    s
    -0.08
     surv
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.22
    æľīä»»ä½ķ
    0.18
    ä»»ä½ķ人
    0.17
    anything
    0.16
    ä»»ä½ķ
    0.16
     anything
    0.14
    ä»»ä½ķä¸Ģ个
    0.14
    åĵªæĢķ
    0.13
     ANY
    0.13
    åĵªæĢķæĺ¯
    0.13
    Activations Density 0.070%

    No Known Activations