© 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. 115235
    Prev
    Next
    INDEX
    Explanations

    sponsor or financing

    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
    .ylim
    -0.09
    ismet
    -0.08
     clocks
    -0.08
    Stars
    -0.08
    sla
    -0.08
     Claw
    -0.08
     Watts
    -0.08
     Witt
    -0.08
    anza
    -0.07
     Hubb
    -0.07
    POSITIVE LOGITS
     yourself
    0.13
     spons
    0.13
     sponsored
    0.11
     sponsor
    0.11
     mentor
    0.10
     sidelines
    0.10
     reimb
    0.10
     financed
    0.10
    aper
    0.10
    /ws
    0.10
    Activations Density 0.001%

    No Known Activations