© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21469
    Prev
    Next
    INDEX
    Explanations

    questions followed by answers

    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
     ??
    -0.08
     (?)
    -0.08
    ä¸ĢæŦ
    -0.08
    ä¸įå¾Ĺä¸į
    -0.08
    缸åºĶ
    -0.08
    ä¸ĢéĿ¢
    -0.07
    ä½Ĩä»į
    -0.07
    ä¸Ģ大æī¹
    -0.07
     arab
    -0.07
     ##
    -0.07
    POSITIVE LOGITS
    é£İæ³¢
    0.10
    edis
    0.10
    è¿Ļ个éĹ®é¢ĺ
    0.10
    åħ¬åı¸ç«łç¨ĭ
    0.10
    æľīåĬ©
    0.10
     ÙĪÙħا
    0.10
    ç»Ħç»ĩé¢Ĩ导
    0.10
    ä¹ĭäºī
    0.10
    æľīä½ķ
    0.10
    ç¿İ
    0.10
    Activations Density 0.403%

    No Known Activations