© 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. 33228
    Prev
    Next
    INDEX
    Explanations

    until, unless, except

    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
     Ups
    -0.11
     dens
    -0.10
    ubar
    -0.10
    strom
    -0.09
    ibal
    -0.09
    LOGGER
    -0.09
    Ups
    -0.09
    ichel
    -0.09
    ses
    -0.09
     pró
    -0.09
    POSITIVE LOGITS
     until
    0.37
     unless
    0.35
    until
    0.35
     except
    0.33
     Until
    0.29
     Except
    0.29
    unless
    0.29
    Until
    0.28
    except
    0.27
    Except
    0.26
    Activations Density 0.137%

    No Known Activations