© 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. 17868
    Prev
    Next
    INDEX
    Explanations

    cutting and related actions

    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
    ấ
    -0.09
     interchangeable
    -0.09
    LC
    -0.09
     Banc
    -0.09
     ups
    -0.09
    unas
    -0.09
     interchange
    -0.09
     Ore
    -0.09
     reim
    -0.09
     Shake
    -0.09
    POSITIVE LOGITS
     cutting
    0.19
     scissors
    0.18
    Cut
    0.17
     Cut
    0.17
     Cutting
    0.17
    cut
    0.16
     cuts
    0.16
    -cut
    0.15
     cut
    0.15
     cutter
    0.15
    Activations Density 0.216%

    No Known Activations