© 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. 91478
    Prev
    Next
    INDEX
    Explanations

    colors and their descriptions

    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
     stren
    -0.10
    ammer
    -0.10
     kne
    -0.10
     genu
    -0.09
     Barnes
    -0.09
     Howe
    -0.09
    append
    -0.09
     slower
    -0.09
     moo
    -0.09
    rott
    -0.09
    POSITIVE LOGITS
    ish
    0.19
    -ish
    0.15
    /nav
    0.13
    ISH
    0.13
    -and
    0.12
     predominant
    0.12
     dominates
    0.11
     highlights
    0.11
    /y
    0.11
     accents
    0.11
    Activations Density 0.074%

    No Known Activations