© 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. 5105
    Prev
    Next
    INDEX
    Explanations

    every turn, around the corner

    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
    æĥħèĬĤ
    -0.09
    éĢł
    -0.09
    å«
    -0.09
    icy
    -0.09
    çļĦè¡£æľį
    -0.08
    pyx
    -0.08
    æ±
    -0.08
    競
    -0.08
    解å¼Ģ
    -0.08
    æĿª
    -0.08
    POSITIVE LOGITS
    ä¸ĢéĿ¢
    0.13
    æ¯ıä¸Ģ
    0.12
    å¤Ħå¤Ħ
    0.12
    ä¸ĢæŃ¥
    0.11
    antis
    0.11
    RSS
    0.10
    è¹ĩ
    0.10
    çļĦä¸ĢéĿ¢
    0.10
    ä¸Ģå¤Ħ
    0.10
    èĥ¥
    0.09
    Activations Density 0.045%

    No Known Activations