© 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. 33924
    Prev
    Next
    INDEX
    Explanations

    left or right side

    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
    è·¸
    -0.09
    Appearance
    -0.08
    _ta
    -0.08
    å¤ĸè§Ĥ
    -0.08
    大çIJĨ
    -0.08
    ä¸įéĢļ
    -0.08
    æĹ©æĻļ
    -0.08
     Shooting
    -0.08
    å½ĵéĢī
    -0.08
    Disclosure
    -0.08
    POSITIVE LOGITS
    æĺİçıł
    0.10
    åı³è¾¹
    0.10
    åľ¨æĹ¥æľ¬
    0.09
    åı³ä¾§
    0.09
    åĮĸçŁ³
    0.09
    åľ¨ä¸Ĭæµ·
    0.08
    æĭ¦
    0.08
     Salv
    0.08
    lients
    0.08
    dx
    0.08
    Activations Density 0.039%

    No Known Activations