© 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. 14783
    Prev
    Next
    INDEX
    Explanations

    Victoria Cross, Victorian mansion

    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
    yard
    -0.10
    nds
    -0.09
    nd
    -0.09
    al
    -0.08
    /tutorial
    -0.08
    alam
    -0.08
    ioned
    -0.08
    ments
    -0.08
    /register
    -0.08
    wash
    -0.08
    POSITIVE LOGITS
    enso
    0.12
    ORK
    0.11
    isle
    0.11
    ENTE
    0.10
    IOUS
    0.10
    ilyn
    0.10
    opher
    0.10
    ively
    0.10
    ORIA
    0.10
     Melbourne
    0.10
    Activations Density 0.083%

    No Known Activations