© 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. 91751
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    bie
    -0.10
    inea
    -0.10
    bung
    -0.10
    yen
    -0.10
    _IL
    -0.10
    ç²
    -0.09
    iane
    -0.09
    TRY
    -0.09
    zar
    -0.09
    AILABLE
    -0.09
    POSITIVE LOGITS
     fug
    0.09
     gro
    0.08
    -Smith
    0.08
     Gard
    0.08
    omba
    0.08
     honors
    0.08
    /pre
    0.08
     opp
    0.08
     til
    0.08
    gard
    0.08
    Activations Density 0.018%

    No Known Activations