© 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. 26337
    Prev
    Next
    INDEX
    Explanations

    title, text, claims, known, written

    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
     curiosity
    -0.11
     rivalry
    -0.11
    Interesting
    -0.11
     penchant
    -0.11
     spotting
    -0.10
     peek
    -0.10
     odd
    -0.10
     mischief
    -0.10
     nudity
    -0.10
     fraught
    -0.10
    POSITIVE LOGITS
     perfected
    0.11
     customizable
    0.11
     massage
    0.10
     Comb
    0.10
     specially
    0.10
     unlimited
    0.10
     hands
    0.10
     interactive
    0.10
     Interactive
    0.10
     Your
    0.10
    Activations Density 0.002%

    No Known Activations