© 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. 91558
    Prev
    Next
    INDEX
    Explanations

    main + purpose/focus

    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
    ugo
    -0.12
     ultimate
    -0.10
     typical
    -0.10
     Mane
    -0.10
    ¢åįķ
    -0.09
     Freeman
    -0.09
    eto
    -0.09
     Approach
    -0.08
    :(
    -0.08
     typically
    -0.08
    POSITIVE LOGITS
    stay
    0.21
     reason
    0.20
     focus
    0.15
     thrust
    0.15
     contributor
    0.15
     conce
    0.15
     concern
    0.14
     source
    0.14
    /main
    0.13
     motiv
    0.12
    Activations Density 0.096%

    No Known Activations