© 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. 5441
    Prev
    Next
    INDEX
    Explanations

    physiologic effects or ownership

    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
    otime
    -0.09
    ä¸Ģå°ģä¿¡
    -0.09
    ä¸įæĸŃåıijå±ķ
    -0.09
    æĪijå¾Ī
    -0.09
    akin
    -0.08
    ä¸Ģçķª
    -0.08
    ä½Ĩä¸įéĻIJ
    -0.08
    мÑĥ
    -0.08
    马æĭī
    -0.08
    heim
    -0.08
    POSITIVE LOGITS
    åīįè¿Ľ
    0.10
    æ³ķåħ°
    0.10
    æĺ¯ä»İ
    0.10
    ä½ľæ¡Ī
    0.09
    มาà¸Īาà¸ģ
    0.08
    ä¹ĭ家
    0.08
    竦
    0.08
    зн
    0.08
    ovic
    0.08
    wers
    0.08
    Activations Density 0.741%

    No Known Activations