© 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. 49572
    Prev
    Next
    INDEX
    Explanations

    male anatomy and programming

    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
    -Smith
    -0.08
     coh
    -0.08
    experience
    -0.07
    .bam
    -0.07
     dal
    -0.07
    oling
    -0.07
    Hur
    -0.07
    IID
    -0.07
     Kathleen
    -0.07
    grunt
    -0.07
    POSITIVE LOGITS
     rising
    0.11
     procure
    0.11
     diff
    0.11
     (>
    0.10
     Diff
    0.10
    Diff
    0.10
    —which
    0.10
     (#
    0.10
     tucked
    0.10
    /button
    0.10
    Activations Density 0.005%

    No Known Activations