© 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. 27620
    Prev
    Next
    INDEX
    Explanations

    stroke defined, is, volume

    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
    çĦ¶æĺ¯
    -0.11
    ities
    -0.11
    HING
    -0.09
    acle
    -0.09
    lector
    -0.09
    irm
    -0.09
    èľ·
    -0.09
    ãģıãĤĮ
    -0.09
    CAPE
    -0.09
    ëģĶ
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    manship
    0.13
    æ´Ĺ礼
    0.11
    abb
    0.10
    busters
    0.09
    ern
    0.09
    æ°Ļ
    0.09
    ç»ıæŁ¥
    0.08
    çĹķ
    0.08
    able
    0.08
    Activations Density 0.025%

    No Known Activations