© 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. 28845
    Prev
    Next
    INDEX
    Explanations

    WITHOUT WARRANTY

    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
    aggi
    -0.10
    GD
    -0.10
    Prostit
    -0.10
    ensa
    -0.10
    acom
    -0.09
    agle
    -0.09
    sla
    -0.09
     costume
    -0.09
    ensi
    -0.09
    abar
    -0.09
    POSITIVE LOGITS
     rag
    0.09
     Cra
    0.08
     lik
    0.08
     gn
    0.08
     chancellor
    0.08
    elle
    0.08
     Rag
    0.08
     Hubb
    0.07
    ê
    0.07
     sustain
    0.07
    Activations Density 2.657%

    No Known Activations