© 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. 30360
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    åį´
    -0.10
    å°¤åħ¶æĺ¯åľ¨
    -0.10
    çī¹åĪ«æĺ¯åľ¨
    -0.10
    åį´æĺ¯
    -0.09
    被æ·ĺæ±°
    -0.09
    itals
    -0.09
    åį»
    -0.08
    åĶ¤
    -0.08
    è¢Ĵ
    -0.08
    çľ¼ç¥ŀ
    -0.08
    POSITIVE LOGITS
    æľīéĻIJåħ¬åı¸
    0.12
    çļĦä¸Ģ大
    0.09
     LLC
    0.08
    ä¸Ģ缴éĥ½
    0.08
    .parseInt
    0.08
    姿
    0.08
    olson
    0.08
    æĺ¯ä¸Ģ家
    0.08
    åīįåĪĹ
    0.08
    à¸Īำà¸ģ
    0.08
    Activations Density 0.106%

    No Known Activations