© 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. 16589
    Prev
    Next
    INDEX
    Explanations

    percentages

    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
    icas
    -0.10
     approximately
    -0.08
     Flynn
    -0.08
     Gould
    -0.08
     Fin
    -0.08
    jin
    -0.08
     enc
    -0.08
     raised
    -0.08
     roughly
    -0.08
     cal
    -0.07
    POSITIVE LOGITS
    Iss
    0.12
     Iss
    0.12
    orno
    0.11
    .Builder
    0.10
    aget
    0.10
     vanity
    0.10
     Cone
    0.09
    Https
    0.09
    fir
    0.09
    rum
    0.09
    Activations Density 0.328%

    No Known Activations