© 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. 91980
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific punctuation or 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
    utsch
    -0.09
     Holl
    -0.08
    ulty
    -0.08
    isper
    -0.08
    ucci
    -0.08
     tub
    -0.08
    andom
    -0.08
    atr
    -0.07
    _import
    -0.07
     Gan
    -0.07
    POSITIVE LOGITS
    —for
    0.11
    berger
    0.11
    arb
    0.10
     dominant
    0.10
     Smy
    0.10
     sne
    0.09
     copp
    0.09
    indx
    0.09
     Sne
    0.09
     egregious
    0.09
    Activations Density 0.003%

    No Known Activations