© 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. 28519
    Prev
    Next
    INDEX
    Explanations

    Summer School randomized study

    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
     lookout
    -0.08
     dryer
    -0.08
     bounty
    -0.07
     Lorenzo
    -0.07
    arges
    -0.07
     Burst
    -0.07
    lint
    -0.07
     chimney
    -0.07
     Mitt
    -0.07
     weak
    -0.07
    POSITIVE LOGITS
     tit
    0.12
     mata
    0.11
     ATI
    0.11
     nir
    0.11
    /host
    0.11
    atto
    0.11
     onstage
    0.11
    /drivers
    0.11
    -API
    0.11
    dance
    0.10
    Activations Density 0.001%

    No Known Activations