© 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. 22739
    Prev
    Next
    INDEX
    Explanations

    opportunities for, room while, explain in, point, voted

    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
    æĥ¯
    -0.11
    è¿Ļ家åħ¬åı¸
    -0.10
    æŀī
    -0.10
    æĺ¥å¤©
    -0.10
    åºĬä¸Ĭ
    -0.09
    æŃ»åİ»
    -0.09
    éŨæĪ·
    -0.09
    åѱ
    -0.09
    upil
    -0.09
    styleType
    -0.09
    POSITIVE LOGITS
    人æµģ
    0.11
    æĹ¶æ®µ
    0.09
    ä¸İåħ¶ä»ĸ
    0.09
    è§ĴèIJ½
    0.09
    åľºåľ°
    0.08
    å±ķä½į
    0.08
    period
    0.08
    åħij
    0.08
    ä¸Ģ对
    0.08
    éĢĹ
    0.08
    Activations Density 0.053%

    No Known Activations