© 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. 15679
    Prev
    Next
    INDEX
    Explanations

    hen followed by names or places

    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
    licht
    -0.09
    ulas
    -0.09
    aar
    -0.08
    ogle
    -0.08
     exact
    -0.08
    splash
    -0.08
    orsk
    -0.08
    iable
    -0.07
     Exact
    -0.07
    ariat
    -0.07
    POSITIVE LOGITS
    andez
    0.14
    hawk
    0.12
    holds
    0.12
    rique
    0.12
    lein
    0.12
    bane
    0.12
    kart
    0.12
    kus
    0.11
    rikes
    0.11
    üz
    0.11
    Activations Density 0.041%

    No Known Activations