© 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. 6431
    Prev
    Next
    INDEX
    Explanations

    names following "named"

    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
     Mark
    -0.09
     Alic
    -0.09
     Denis
    -0.08
     Frank
    -0.08
     Travis
    -0.08
     Stuart
    -0.08
     Lane
    -0.08
     Craig
    -0.08
     Hilton
    -0.07
     Scott
    -0.07
    POSITIVE LOGITS
     Orwell
    0.12
    quota
    0.12
    nym
    0.10
     Alps
    0.10
     Sahara
    0.10
    Parms
    0.10
    ifa
    0.10
     numbering
    0.10
    subs
    0.10
    ODO
    0.10
    Activations Density 0.193%

    No Known Activations