© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48995
    Prev
    Next
    INDEX
    Explanations

    Allen followed by punctuation or 'et al'

    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
    CKET
    -0.08
     little
    -0.08
    dif
    -0.08
    imize
    -0.08
    aly
    -0.08
     skim
    -0.08
    LER
    -0.07
     ver
    -0.07
    éĹ´
    -0.07
    lew
    -0.07
    POSITIVE LOGITS
    ../
    0.11
    .xmlbeans
    0.11
    ogens
    0.11
    plet
    0.11
    ship
    0.11
    erator
    0.10
    orsk
    0.10
    ships
    0.10
    lijke
    0.10
    finite
    0.10
    Activations Density 0.294%

    No Known Activations