© 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. 6419
    Prev
    Next
    INDEX
    Explanations

    whole operation or thing

    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
    ern
    -0.09
    kowski
    -0.09
    纨
    -0.08
    çłĶ究æĬ¥åijĬ
    -0.08
    æŁ¯
    -0.08
     ppt
    -0.08
    inne
    -0.08
    çªĸ
    -0.08
    çļĦåľŁåľ°
    -0.08
    ãĥ©ãĥ³ãĥī
    -0.08
    POSITIVE LOGITS
    æ®Ĭ
    0.11
    æķ´ä½ĵ
    0.10
    ey
    0.09
    çīĪæĿĥå½Ĵ
    0.09
    ì°½
    0.09
    å°§
    0.09
     дело
    0.09
     Canter
    0.09
    ä¸ĭæĿ¥
    0.08
    è¿ĩç¨ĭ
    0.08
    Activations Density 0.101%

    No Known Activations