© 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. 117120
    Prev
    Next
    INDEX
    Explanations

    file paths, code, or JSON data

    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
     animation
    -0.09
     reinterpret
    -0.08
     gib
    -0.08
     clap
    -0.08
     slo
    -0.08
     animations
    -0.08
     fren
    -0.07
     rag
    -0.07
     liberal
    -0.07
    animation
    -0.07
    POSITIVE LOGITS
    sez
    0.10
    &q
    0.10
     errorThrown
    0.09
    thalm
    0.09
    igli
    0.09
    kov
    0.09
    efa
    0.08
    grave
    0.08
    iks
    0.08
     tslint
    0.08
    Activations Density 0.006%

    No Known Activations