© 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. 56454
    Prev
    Next
    INDEX
    Explanations

    now!

    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
     ÑĤепеÑĢÑĮ
    -0.11
    KIT
    -0.10
    æĭĩ
    -0.09
    ç½ijåºĹ
    -0.09
    ä¸įçķĻ
    -0.09
    oned
    -0.09
    chy
    -0.09
    æĩĭ
    -0.09
    eken
    -0.09
    ноÑģÑĤей
    -0.09
    POSITIVE LOGITS
    fix
    0.08
    ä¸Ńä»ĭ
    0.07
    hin
    0.07
    blk
    0.07
    为人
    0.07
    etch
    0.07
    ouv
    0.07
    è´²
    0.07
    SEQ
    0.07
     conf
    0.07
    Activations Density 0.002%

    No Known Activations