© 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. 29924
    Prev
    Next
    INDEX
    Explanations

    it was / it's / it just

    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
    .ss
    -0.11
     proof
    -0.10
     Proof
    -0.10
    ogo
    -0.10
    ¢
    -0.10
     Tele
    -0.10
     Dat
    -0.09
     hired
    -0.09
    ess
    -0.09
     scissors
    -0.09
    POSITIVE LOGITS
     never
    0.11
     shouldn
    0.10
     hasn
    0.09
     seldom
    0.09
     stayed
    0.09
     always
    0.09
     Fried
    0.09
     NEVER
    0.09
     stays
    0.09
    achi
    0.09
    Activations Density 0.064%

    No Known Activations