© 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. 4964
    Prev
    Next
    INDEX
    Explanations

    referring to a group

    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
    çķª
    -0.09
    çİ¥
    -0.09
    ç¨ļ
    -0.09
    ìį¨
    -0.08
    ãģĬãģĭ
    -0.08
    车å±ķ
    -0.08
     jeder
    -0.08
    妲
    -0.08
    ookie
    -0.08
    æĹ¶è®¸
    -0.08
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.19
    æĿ¥è¯´
    0.18
    çݩ家æĿ¥è¯´
    0.16
    æĪĺ士æĿ¥è¯´
    0.15
    ä¾Ĩ說
    0.13
    æĿ¥è®²
    0.13
    èĢĮè¨Ģ
    0.12
    æĤĴ
    0.09
    è§Ĵ度æĿ¥çľĭ
    0.09
    ngth
    0.09
    Activations Density 0.042%

    No Known Activations