© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24088
    Prev
    Next
    INDEX
    Explanations

    body parts used for grasping

    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
    Negative Logits
    æľīåIJį
    -0.10
    å®ĺ
    -0.10
    éĴĵ
    -0.10
    Angel
    -0.09
    æĺİ天
    -0.09
    éĶ¦ç»£
    -0.08
    ç»ĻåĪ«äºº
    -0.08
    ä¹¾åĿ¤
    -0.08
    elli
    -0.08
    Stub
    -0.08
    POSITIVE LOGITS
    é¹Ń
    0.09
    èĹ©
    0.09
    æĨ¾
    0.09
    对æłĩ
    0.09
    Cancelable
    0.09
    奢
    0.09
    ç¾¼
    0.08
    ç¥Ŀè´º
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    èħ°
    0.08
    Activations Density 0.057%

    No Known Activations