© 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. 39621
    Prev
    Next
    INDEX
    Explanations

    separates clauses or items

    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
    好äºĭ
    -0.10
    åį´è¢«
    -0.10
    éĵĭ
    -0.09
    å°±æĬĬ
    -0.09
    `t
    -0.09
    ä»ĸä»¬åľ¨
    -0.08
    èĽ°
    -0.08
    åĩłä¹İæīĢæľī
    -0.08
    åĿĩå·²
    -0.08
    æĪijæĬĬ
    -0.08
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģç§į
    0.12
    æľ¬èº«
    0.11
    arez
    0.11
    çļĦä¸ĢåĪĩ
    0.10
    пÑĢавлÑı
    0.10
    åıĬåħ¶
    0.10
    çļĦçī¹çĤ¹
    0.09
    çļĦä¸Ģ个
    0.09
    æľ¬èº«çļĦ
    0.09
    æĺ¯ä¸Ģç§į
    0.09
    Activations Density 0.153%

    No Known Activations