© 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. 51166
    Prev
    Next
    INDEX
    Explanations

    permission to use, copy, modify, distribute

    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
    ä¸įéĶĪ
    -0.09
    çĿ¥
    -0.09
    _ENCODING
    -0.08
    é¢Ĩ导
    -0.08
     McDon
    -0.08
    èĥ½æī¾åĪ°
    -0.08
    æ£ļ
    -0.08
     decre
    -0.08
    çĸ½
    -0.08
    LABEL
    -0.08
    POSITIVE LOGITS
    éŁª
    0.09
    èĢ¸
    0.09
    æ±Ĺ
    0.09
    滥çĶ¨
    0.09
    iew
    0.08
    eyJ
    0.08
    CDATA
    0.08
    .eclipse
    0.08
    è¿ĽéŨ
    0.08
    äºĽè®¸
    0.08
    Activations Density 0.083%

    No Known Activations