© 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. 16973
    Prev
    Next
    INDEX
    Explanations

    introduction into or onto

    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
    apr
    -0.11
    avn
    -0.11
     genu
    -0.11
    UDA
    -0.11
    -relative
    -0.10
    -handle
    -0.10
     IQueryable
    -0.10
    ajas
    -0.10
    stants
    -0.10
    ideshow
    -0.10
    POSITIVE LOGITS
     transferred
    0.16
     transfer
    0.16
     deposited
    0.14
     into
    0.14
    into
    0.13
     Into
    0.13
     absorbed
    0.13
    transfer
    0.12
    Transfer
    0.12
     Transfer
    0.12
    Activations Density 0.234%

    No Known Activations