© 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. 47150
    Prev
    Next
    INDEX
    Explanations

    original container or packaging

    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
    Bearer
    -0.11
     conventions
    -0.10
    oti
    -0.09
    Convention
    -0.09
     trem
    -0.09
    isons
    -0.09
    ecret
    -0.09
    assi
    -0.09
     Harris
    -0.09
     Diane
    -0.09
    POSITIVE LOGITS
     supplied
    0.16
     provided
    0.15
     original
    0.15
     factory
    0.12
    provided
    0.12
    Disc
    0.12
     Disc
    0.12
     shipped
    0.12
     upright
    0.11
    Original
    0.11
    Activations Density 0.019%

    No Known Activations