© 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. 17250
    Prev
    Next
    INDEX
    Explanations

    proportion

    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
     Vanguard
    -0.10
    orris
    -0.10
     Ballard
    -0.09
    acam
    -0.09
    igne
    -0.09
    veh
    -0.09
    jad
    -0.09
    ettes
    -0.09
    /show
    -0.09
    ved
    -0.09
    POSITIVE LOGITS
    ately
    0.26
    ate
    0.18
    ally
    0.15
    ality
    0.13
    ATE
    0.12
    edly
    0.12
    ratio
    0.11
     (%)
    0.10
    ably
    0.10
     Haz
    0.10
    Activations Density 0.082%

    No Known Activations