© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89708
    Prev
    Next
    INDEX
    Explanations

    overview of

    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
    ivant
    -0.09
    ings
    -0.09
    ae
    -0.08
    azzo
    -0.08
    rag
    -0.08
    elo
    -0.08
     Props
    -0.08
     Angus
    -0.08
    误
    -0.08
    eu
    -0.08
    POSITIVE LOGITS
    ĵ
    0.10
     Leopard
    0.10
    oenix
    0.10
    ductory
    0.10
     nervous
    0.10
     squat
    0.10
    dot
    0.09
     thereof
    0.09
    acock
    0.09
    ------------
    0.09
    Activations Density 0.034%

    No Known Activations