© 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. 49115
    Prev
    Next
    INDEX
    Explanations

    reviews and recommendations

    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
     Reviews
    -0.19
     reviews
    -0.18
    Reviews
    -0.16
    _review
    -0.15
     review
    -0.15
     reviewed
    -0.14
    _reviews
    -0.14
    reviews
    -0.13
     reviewing
    -0.13
     Reviewed
    -0.13
    POSITIVE LOGITS
     Mirage
    0.11
    elig
    0.11
     photos
    0.11
    egis
    0.10
     Jag
    0.10
     Baxter
    0.10
     Gent
    0.10
     competitor
    0.10
     milit
    0.10
    iform
    0.10
    Activations Density 0.020%

    No Known Activations