© 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. 39184
    Prev
    Next
    INDEX
    Explanations

    currentstandards

    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
    .mozilla
    -0.09
    chy
    -0.09
    æīĺ管
    -0.08
    ä¿Ŀåį«
    -0.08
    eon
    -0.08
    agi
    -0.08
    æīĵäºĨ
    -0.08
    åIJįçīĩ
    -0.08
    Seen
    -0.07
    鲤
    -0.07
    POSITIVE LOGITS
    修订
    0.13
    ç»ĨåĪĻ
    0.13
    æĻ¦
    0.12
    åĽ½å®¶æłĩåĩĨ
    0.11
    èįīæ¡Ī
    0.11
    éĢĤçĶ¨äºİ
    0.11
    æĮĩå¼ķ
    0.11
    å®ŀæĸ½ç»ĨåĪĻ
    0.11
    æľĢæĸ°
    0.10
     standards
    0.10
    Activations Density 0.117%

    No Known Activations