© 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. 6446
    Prev
    Next
    INDEX
    Explanations

    cut and related words

    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
    ged
    -0.09
    ayed
    -0.09
    esser
    -0.08
    s
    -0.08
     AIM
    -0.08
    Ø´
    -0.07
    á»ĵ
    -0.07
    IED
    -0.07
     Schwe
    -0.07
     Rev
    -0.07
    POSITIVE LOGITS
     cut
    0.20
     CUT
    0.18
     Cut
    0.17
    =cut
    0.16
    -cut
    0.16
    .cut
    0.16
    Cut
    0.15
    cut
    0.15
    throat
    0.15
     cutoff
    0.14
    Activations Density 0.008%

    No Known Activations