© 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. 27032
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    llvm
    -0.09
    ä¸ĢæŃ¥
    -0.08
    æ¯ıå¹´
    -0.08
    åĶ®ä»·
    -0.08
    åīįåIJİ
    -0.08
    èĥ½ä¸įèĥ½
    -0.08
    unts
    -0.07
    èī¯å¿ĥ
    -0.07
    æijĩ
    -0.07
     Ñĥме
    -0.07
    POSITIVE LOGITS
    è¿Ļä¸Ģå¹´
    0.12
    åħ¨å¹´
    0.11
    äºĨå¤ļå°ij
    0.10
    大å®Ĺ
    0.10
    æħij
    0.10
    éĢĨåĬ¿
    0.09
    åľ¨è¿ĩåİ»
    0.09
    åīįä¸īåŃ£åº¦
    0.09
    åĴ¨
    0.09
    æįįåį«
    0.09
    Activations Density 0.162%

    No Known Activations