© 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. 54712
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
    æĺ¥ç§ĭ
    -0.09
    欣
    -0.09
    è¾ķ
    -0.09
    Flo
    -0.09
    ARD
    -0.08
    ç»ĩ
    -0.08
    å½ĵæĪij
    -0.08
    onor
    -0.08
    弥补
    -0.08
    çĨ¨
    -0.08
    POSITIVE LOGITS
    æīĵæĸŃ
    0.11
    æľ¬èº«çļĦ
    0.10
    æĶ¹åıĺäºĨ
    0.10
    æ´Ĺ礼
    0.10
    ä½ľæģ¯
    0.09
    çĽ
    0.09
    èĩªèº«çļĦ
    0.09
    迫使
    0.09
    èģĮä½į
    0.09
    æ´»çĿĢ
    0.09
    Activations Density 0.163%

    No Known Activations