© 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. 22405
    Prev
    Next
    INDEX
    Explanations

    technical concepts and workflows

    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
    çŀ¥
    -0.08
    storm
    -0.08
    oten
    -0.08
    umbo
    -0.08
    Fri
    -0.08
    ä¸ºæł¸å¿ĥçļĦ
    -0.08
    wich
    -0.08
    (PHP
    -0.07
    æĤŁ
    -0.07
    (es
    -0.07
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.10
    VERS
    0.09
    天ä¸Ĭ
    0.09
    ULT
    0.09
    å¥
    0.08
    绽
    0.08
    æ§
    0.08
    emet
    0.08
    eking
    0.08
    åIJĬ
    0.08
    Activations Density 0.389%

    No Known Activations