© 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. 1674
    Prev
    Next
    INDEX
    Explanations

    opponent / opponents

    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
    è¡·
    -0.13
    æĦİ
    -0.11
    point
    -0.09
    ier
    -0.09
    éļ¶å±ŀäºİ
    -0.09
    åı¦å¤ĸä¸Ģ个
    -0.09
    brook
    -0.09
    otype
    -0.09
    otte
    -0.09
    ÑĢабоÑĤ
    -0.09
    POSITIVE LOGITS
    ely
    0.09
    sWith
    0.09
    arium
    0.09
    ship
    0.08
    qrst
    0.08
    nel
    0.08
    ents
    0.08
    éĺ¿éĩĮ
    0.08
    kea
    0.08
    gether
    0.08
    Activations Density 0.008%

    No Known Activations