© 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. 15374
    Prev
    Next
    INDEX
    Explanations

    retrospective

    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
    oly
    -0.07
     Whites
    -0.07
    udd
    -0.07
     pend
    -0.07
     sinister
    -0.07
    armor
    -0.07
     flown
    -0.07
    rio
    -0.07
     reputation
    -0.07
    ole
    -0.07
    POSITIVE LOGITS
    pectives
    0.14
    (ret
    0.14
    pective
    0.13
    arget
    0.13
    ention
    0.13
    renched
    0.12
    .Ret
    0.12
    illard
    0.12
    angular
    0.12
    irie
    0.12
    Activations Density 0.143%

    No Known Activations