© 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. 29877
    Prev
    Next
    INDEX
    Explanations

    downloading things

    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
     Ñģобой
    -0.11
    idon
    -0.10
    ÑģÑĤвоваÑĤÑĮ
    -0.09
    ãĥªãĥ³ãĤ°
    -0.09
    çĩİ
    -0.08
    aight
    -0.08
    lessly
    -0.08
    ucking
    -0.08
    ¼
    -0.08
    irt
    -0.08
    POSITIVE LOGITS
    ä¸ĭæĿ¥
    0.10
    å¼ıçļĦ
    0.10
    ä¸ĭæĿ¥çļĦ
    0.10
    sWith
    0.09
    缨
    0.09
    OrCreate
    0.09
    .Download
    0.09
    /upload
    0.09
    ToDevice
    0.09
    æ¸Ń
    0.09
    Activations Density 0.044%

    No Known Activations