© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    departments or fields of study

    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
    iglia
    -0.10
    çī¹æĿĥ
    -0.09
    lus
    -0.09
    èĦ±ç¦»
    -0.09
    æĢ»è®¡
    -0.09
     Kapoor
    -0.09
    rored
    -0.08
    JC
    -0.08
    chts
    -0.08
    atee
    -0.08
    POSITIVE LOGITS
    é¢ĨåŁŁçļĦ
    0.10
    æĿ¿åĿĹ
    0.10
    é¢ĨåŁŁ
    0.09
    箪
    0.09
     cou
    0.09
    ä¸Ģç³»åĪĹ
    0.09
     SimpleName
    0.09
    _anchor
    0.08
    berman
    0.08
    ãĤº
    0.08
    Activations Density 0.130%

    No Known Activations