© 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. 88084
    Prev
    Next
    INDEX
    Explanations

    how, why, what, whether

    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
     unspecified
    -0.08
    anio
    -0.08
    echa
    -0.08
     Smooth
    -0.07
    ansk
    -0.07
    izar
    -0.07
    agn
    -0.07
    ena
    -0.07
     incom
    -0.06
    .ip
    -0.06
    POSITIVE LOGITS
     how
    0.50
     why
    0.39
    how
    0.37
     whether
    0.34
     what
    0.30
    why
    0.29
     WHY
    0.27
     cómo
    0.27
     HOW
    0.26
    whether
    0.26
    Activations Density 0.351%

    No Known Activations