© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33527
    Prev
    Next
    INDEX
    Explanations

    curl, cur, corp, curtmisc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    à¸ĸ
    -0.11
    mond
    -0.09
     contr
    -0.08
    igate
    -0.08
     dh
    -0.08
    imate
    -0.08
    roz
    -0.08
     Chess
    -0.08
     doub
    -0.07
     Buddhist
    -0.07
    POSITIVE LOGITS
     Cur
    0.20
    -cur
    0.19
     CUR
    0.18
     cur
    0.18
     curl
    0.18
     Curl
    0.18
    Cur
    0.18
    .cur
    0.17
    [cur
    0.17
     curvature
    0.16
    Activations Density 0.052%

    No Known Activations