© 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. 48148
    Prev
    Next
    INDEX
    Explanations

    in accordance or in addition

    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
     Howell
    -0.12
    antly
    -0.10
     silently
    -0.09
     vex
    -0.09
     Vent
    -0.09
    ¢
    -0.09
    icans
    -0.09
     ye
    -0.09
     Resets
    -0.09
    succ
    -0.09
    POSITIVE LOGITS
     contexts
    0.10
    (strict
    0.09
     Bris
    0.08
    --[
    0.08
     Roe
    0.08
     hob
    0.08
    abr
    0.08
     regulated
    0.08
    Won
    0.08
    controlled
    0.08
    Activations Density 0.002%

    No Known Activations