© 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. 25553
    Prev
    Next
    INDEX
    Explanations

    expert opinion or world

    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
    —you
    -0.16
     your
    -0.13
     you
    -0.13
     Your
    -0.12
     You
    -0.12
     forget
    -0.11
     Choose
    -0.11
     easy
    -0.11
     choose
    -0.11
     Prepare
    -0.11
    POSITIVE LOGITS
     Generally
    0.12
     arguably
    0.12
    Generally
    0.12
     generally
    0.11
     largely
    0.11
     Typically
    0.11
     typically
    0.11
    typically
    0.10
     Redistributions
    0.10
    Ultimately
    0.10
    Activations Density 0.001%

    No Known Activations