© 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. 61341
    Prev
    Next
    INDEX
    Explanations

    installing new

    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
    å¤ļä½Ļ
    -0.10
    æľĿçĿĢ
    -0.09
     Towards
    -0.09
    å¢Ļ
    -0.09
     towards
    -0.09
    _DEPRECATED
    -0.09
    Towards
    -0.08
    å£ģ
    -0.08
    aser
    -0.08
    _UPDATED
    -0.08
    POSITIVE LOGITS
    å¼ķåħ¥
    0.13
    è¿ĽæĿ¥
    0.13
    å®īè£ħ
    0.12
    å¼ķè¿Ľ
    0.11
    éĵºè®¾
    0.10
    èIJ½æĪ·
    0.10
    ãĤĴåħ¥ãĤĮ
    0.10
    åĪ°ä½į
    0.09
    çļĦåĪ°æĿ¥
    0.09
     ìĦ¤ì¹ĺ
    0.09
    Activations Density 0.103%

    No Known Activations