© 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. 91332
    Prev
    Next
    INDEX
    Explanations

    forgive me, excuse me, tell me

    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
     Fires
    -0.10
    oni
    -0.10
    isu
    -0.10
     Herrera
    -0.09
     palette
    -0.09
    odel
    -0.09
    BCM
    -0.09
     Scar
    -0.09
    ran
    -0.09
    uni
    -0.09
    POSITIVE LOGITS
     somehow
    0.12
     Somehow
    0.10
     me
    0.10
    /me
    0.10
     misunder
    0.09
     Duis
    0.09
    ucch
    0.09
     whe
    0.09
     Stadt
    0.09
     ME
    0.08
    Activations Density 0.006%

    No Known Activations