© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3105
    Prev
    Next
    INDEX
    Explanations

    shebang lines for python

    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
    ingly
    -0.12
    æİĮ声
    -0.10
    alah
    -0.09
    åı·
    -0.09
    ties
    -0.09
    ges
    -0.09
    GES
    -0.08
    é¹ij
    -0.08
    ordon
    -0.08
    pped
    -0.08
    POSITIVE LOGITS
    istas
    0.12
    ramid
    0.12
    ista
    0.11
    ASY
    0.11
    aceous
    0.11
    ique
    0.11
    ized
    0.10
    ÑĤеÑĢ
    0.10
    Anywhere
    0.10
    ised
    0.10
    Activations Density 0.203%

    No Known Activations