© 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. 89561
    Prev
    Next
    INDEX
    Explanations

    -- programme, Listener-- infection, on-- infect, ing-- screw, them-- slave, cylinder

    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
    ecs
    -0.10
    mlink
    -0.10
    лÑİ
    -0.08
     persuasion
    -0.08
    zcze
    -0.08
     impro
    -0.08
    spr
    -0.08
     private
    -0.08
    raphic
    -0.08
     McGu
    -0.08
    POSITIVE LOGITS
     relentlessly
    0.12
     loose
    0.12
     tight
    0.11
     aggressively
    0.11
    ubo
    0.11
     loos
    0.11
    hard
    0.10
     into
    0.10
     stunned
    0.10
    _sy
    0.10
    Activations Density 0.006%

    No Known Activations