© 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. 31119
    Prev
    Next
    INDEX
    Explanations

    doctor Who

    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
    noch
    -0.13
    roud
    -0.13
    kir
    -0.12
    esk
    -0.11
    acre
    -0.11
    elor
    -0.11
    yd
    -0.11
    earch
    -0.11
    riet
    -0.11
    -bodied
    -0.10
    POSITIVE LOGITS
    ate
    0.16
     Manhattan
    0.12
    ial
    0.10
    ury
    0.10
     Who
    0.10
    ATE
    0.09
    /ph
    0.09
    /sc
    0.09
    qus
    0.09
    inally
    0.09
    Activations Density 0.085%

    No Known Activations