© 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. 19061
    Prev
    Next
    INDEX
    Explanations

    KBEngine, ircadia, lead weight

    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
    æºľ
    -0.11
    éĹ³
    -0.10
    æĥ³èµ·æĿ¥
    -0.09
    æ»ij
    -0.09
    礼è²Į
    -0.09
    ischer
    -0.09
    éĢĴç»Ļ
    -0.09
    æľŃ
    -0.09
    海滨
    -0.09
    èĮĦ
    -0.09
    POSITIVE LOGITS
    裸
    0.11
     Circus
    0.09
    é¦ĸ
    0.09
    ä¸ĭ游
    0.09
    rush
    0.09
    禽
    0.08
     Kel
    0.08
    追踪
    0.08
    追
    0.08
    æijĴ
    0.08
    Activations Density 0.207%

    No Known Activations