© 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. 18135
    Prev
    Next
    INDEX
    Explanations

    a couple of

    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
     BITS
    -0.10
    .src
    -0.09
    å±ķæľĽ
    -0.08
    ectors
    -0.08
    çĶļ
    -0.08
    ä½ľä¸ºä¸Ģç§į
    -0.08
    ä¸ĬåѦ
    -0.08
     somew
    -0.08
    aira
    -0.08
    ç¿Ķ
    -0.08
    POSITIVE LOGITS
    å±ĤéĿ¢
    0.10
    otch
    0.10
    aler
    0.09
    æĸ°æĬĢæľ¯
    0.08
    è¿IJæ°Ķ
    0.08
    çļĦåĪ©çĽĬ
    0.08
    ãĤ½ãĥ³
    0.08
    æĸ°çļĦ
    0.08
    inus
    0.08
    _HARD
    0.08
    Activations Density 0.007%

    No Known Activations