© 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. 7020
    Prev
    Next
    INDEX
    Explanations

    Tw prefixes

    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
    aurant
    -0.09
     outright
    -0.08
    ption
    -0.08
    .pp
    -0.08
    held
    -0.07
    oller
    -0.07
    à¹Į
    -0.07
     ${(
    -0.07
     aw
    -0.07
    unker
    -0.07
    POSITIVE LOGITS
     tween
    0.12
    inkle
    0.12
    emoji
    0.12
     Tw
    0.11
     twins
    0.11
    inky
    0.11
    ilio
    0.11
    cio
    0.11
    Tw
    0.11
     Styles
    0.11
    Activations Density 0.004%

    No Known Activations