© 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. 19024
    Prev
    Next
    INDEX
    Explanations

    initials followed by names

    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
    andle
    -0.08
    ä»»æĢ§
    -0.08
    éĻ³
    -0.08
    elib
    -0.08
    ëħIJ
    -0.08
    licative
    -0.08
    éĴ¥
    -0.07
    ante
    -0.07
    åĢĻ
    -0.07
    ging
    -0.07
    POSITIVE LOGITS
    frage
    0.10
    ä¸įæħİ
    0.09
     Stamp
    0.09
    åī¡
    0.09
    .DropDown
    0.09
    åĽłä¸ºæĪij们
    0.09
    ä¸ī项
    0.09
     иÑģпол
    0.09
    |--
    0.09
    aur
    0.09
    Activations Density 0.066%

    No Known Activations