© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31358
    Prev
    Next
    INDEX
    Explanations

    letting you do something

    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
    ------↵↵
    -0.11
    ubber
    -0.11
    mux
    -0.11
     Vac
    -0.11
    azo
    -0.11
     Presidency
    -0.10
     laughter
    -0.10
     Bring
    -0.10
    .Mark
    -0.10
    bracht
    -0.10
    POSITIVE LOGITS
     allowing
    0.09
     allow
    0.09
     me
    0.09
    /ca
    0.08
     us
    0.08
     permitting
    0.08
     allows
    0.08
    izens
    0.08
    izia
    0.08
     Stranger
    0.08
    Activations Density 0.024%

    No Known Activations