© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9855
    Prev
    Next
    INDEX
    Explanations

    mounting on supports

    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
    ä¸ĢèĤ¡
    -0.10
    åİ»è¿ĩ
    -0.09
    æĮļ
    -0.09
    IJ
    -0.09
    /null
    -0.09
    èĿĮ
    -0.09
    å¤ĩæ¡Ī
    -0.09
    nal
    -0.09
    è°Į
    -0.08
    ovich
    -0.08
    POSITIVE LOGITS
    aine
    0.14
    ains
    0.10
    astic
    0.10
    ings
    0.09
    gomery
    0.09
    æĪijåıĪ
    0.09
    oggle
    0.09
    ãĤ¥
    0.09
    ering
    0.09
    ments
    0.09
    Activations Density 0.037%

    No Known Activations