© 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. 22817
    Prev
    Next
    INDEX
    Explanations

    that can

    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
     Lantern
    -0.10
    herits
    -0.08
    мÑĭ
    -0.08
    éĢĴ
    -0.08
    ìĦ¤
    -0.08
    ents
    -0.08
     Kens
    -0.08
    vars
    -0.07
    urv
    -0.07
    夹
    -0.07
    POSITIVE LOGITS
    æľīåĪ©äºİ
    0.15
    让èĩªå·±
    0.13
    ä¼ļ导èĩ´
    0.12
    ä¼ļéķ¿
    0.11
    导èĩ´
    0.11
    åIJ¬èµ·æĿ¥
    0.10
    让ä»ĸ们
    0.10
    ä¼ļ使
    0.10
    ä¼ļ产çĶŁ
    0.10
    èĥ½ä½¿
    0.10
    Activations Density 0.104%

    No Known Activations