© 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. 33404
    Prev
    Next
    INDEX
    Explanations

    left end

    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
     subj
    -0.10
     other
    -0.09
    _yes
    -0.08
     trailing
    -0.08
    nika
    -0.08
     orgasm
    -0.08
     afternoon
    -0.08
     NEXT
    -0.08
     Disability
    -0.08
     env
    -0.08
    POSITIVE LOGITS
    sal
    0.11
     front
    0.11
     Front
    0.11
    _front
    0.10
     outer
    0.10
    Front
    0.10
     preamble
    0.10
    Outer
    0.10
    Starting
    0.10
    <|fim_suffix|>
    0.10
    Activations Density 0.586%

    No Known Activations