© 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. 47900
    Prev
    Next
    INDEX
    Explanations

    easier said than done

    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
     termin
    -0.09
    ä¸įçĶ¨æĭħå¿ĥ
    -0.09
    娥
    -0.09
    æµĵåİļ
    -0.09
    è¿ĵ
    -0.08
     pro
    -0.08
    çºĮ
    -0.08
    ä»Ģä¹ĪåİŁåĽł
    -0.08
     associ
    -0.08
    alin
    -0.08
    POSITIVE LOGITS
    åIJ¬èµ·æĿ¥
    0.12
    羣æŃ£åģļåĪ°
    0.12
    éģĵçIJĨ
    0.11
    éļ¾
    0.11
    容æĺĵ
    0.10
     ìī½
    0.10
    éļ¾åº¦
    0.10
    пло
    0.09
    _easy
    0.09
    ç®Ģåįķ
    0.09
    Activations Density 0.198%

    No Known Activations