© 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. 34202
    Prev
    Next
    INDEX
    Explanations

    punishment or negative 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
    umbing
    -0.10
    亡
    -0.09
    ฤ
    -0.09
    æĴĦ
    -0.09
    Ahead
    -0.09
    âļĶ
    -0.09
    ENTS
    -0.09
    åį±
    -0.08
    çĮķ
    -0.08
    æ¦Ľ
    -0.08
    POSITIVE LOGITS
    毫ä¸įçĬ¹è±«
    0.12
    让ä»ĸ们
    0.11
    hof
    0.09
    çĭłçĭł
    0.09
    ä¸ĢçĤ¹ä¹Łä¸į
    0.09
     Sky
    0.09
    å½»åºķ
    0.09
    个å¤ļ
    0.09
    è¶Ĭ
    0.08
    æ§Ľ
    0.08
    Activations Density 0.048%

    No Known Activations