© 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. 117057
    Prev
    Next
    INDEX
    Explanations

    make + consequences

    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
    utto
    -0.10
     deepest
    -0.10
     conclus
    -0.10
    isko
    -0.10
    ijo
    -0.10
    erah
    -0.10
     \`
    -0.09
     Particularly
    -0.09
    avery
    -0.09
     particularly
    -0.09
    POSITIVE LOGITS
     unable
    0.13
     become
    0.13
     able
    0.12
     gain
    0.12
     lose
    0.10
     Able
    0.10
    ode
    0.10
     be
    0.09
     deserve
    0.09
     Gain
    0.09
    Activations Density 0.063%

    No Known Activations