© 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. 47967
    Prev
    Next
    INDEX
    Explanations

    slur, swirl, whirl, flurry

    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
     Palmer
    -0.10
    STE
    -0.10
    gom
    -0.10
     commencement
    -0.09
    stype
    -0.09
    peare
    -0.08
    ented
    -0.08
    SM
    -0.08
    atem
    -0.08
    ocos
    -0.08
    POSITIVE LOGITS
    ping
    0.13
    pool
    0.11
     slur
    0.11
     swirling
    0.11
    ped
    0.10
    led
    0.10
     swirl
    0.10
    ricane
    0.10
    iously
    0.10
     gulp
    0.10
    Activations Density 0.003%

    No Known Activations