© 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. 55640
    Prev
    Next
    INDEX
    Explanations

    get 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
    из
    -0.10
    /out
    -0.10
    ichel
    -0.10
    ä»»ä½ķæŶåĢĻ
    -0.10
    hy
    -0.09
    oute
    -0.09
    ä¹İ
    -0.09
     eget
    -0.09
    æĪij们ä¼ļ
    -0.09
    åıªå¾Ĺ
    -0.09
    POSITIVE LOGITS
     rid
    0.17
    timeofday
    0.15
    tings
    0.15
    ters
    0.14
    TING
    0.12
    tin
    0.12
    aways
    0.12
    PrototypeOf
    0.11
    ä¸Ģ份
    0.11
    ä½ķåĨµ
    0.10
    Activations Density 0.134%

    No Known Activations