© 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. 33490
    Prev
    Next
    INDEX
    Explanations

    refusal, wrote, reminder

    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
     literally
    -0.11
     Prescott
    -0.10
     monopoly
    -0.09
     Needless
    -0.09
    '||
    -0.09
     Thor
    -0.09
     pitched
    -0.09
     literal
    -0.09
    Thor
    -0.09
    itten
    -0.09
    POSITIVE LOGITS
    Stride
    0.10
    HL
    0.09
    awe
    0.09
    ãĥ¼ãĥĪ
    0.09
    alin
    0.09
     callers
    0.09
    (cls
    0.09
    hl
    0.09
     cunning
    0.08
     Shank
    0.08
    Activations Density 0.002%

    No Known Activations