© 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. 30645
    Prev
    Next
    INDEX
    Explanations

    anonymous reader writes

    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
    .§
    -0.10
     emitted
    -0.09
     neg
    -0.09
    elic
    -0.09
    Desk
    -0.09
    Earn
    -0.09
    /provider
    -0.09
    udios
    -0.09
    spell
    -0.09
     Phonetic
    -0.09
    POSITIVE LOGITS
     coward
    0.08
     lur
    0.07
    ëł¥
    0.07
    urge
    0.07
    Anonymous
    0.07
     noreferrer
    0.07
    ppo
    0.07
    zem
    0.07
    keh
    0.07
     flex
    0.07
    Activations Density 0.089%

    No Known Activations