© 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. 28131
    Prev
    Next
    INDEX
    Explanations

    feet measurement

    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
    erate
    -0.11
    eres
    -0.09
    -purpose
    -0.09
    ry
    -0.09
    ity
    -0.09
    éĽİ
    -0.09
    hed
    -0.08
    ette
    -0.08
    ergic
    -0.08
    åİ©
    -0.08
    POSITIVE LOGITS
    BALL
    0.13
    tings
    0.10
    è¸Ŀ
    0.10
    ting
    0.10
    累累
    0.10
    lessness
    0.10
    леÑĩ
    0.09
    æ§Ľ
    0.09
    骤
    0.09
    ÙĪØ·
    0.09
    Activations Density 0.038%

    No Known Activations