© 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. 28484
    Prev
    Next
    INDEX
    Explanations

    cub or tub followed by certain endings

    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
    unas
    -0.07
     dor
    -0.07
    ISO
    -0.07
    ustin
    -0.07
    geist
    -0.07
    ener
    -0.07
    -floating
    -0.07
    inned
    -0.06
    /we
    -0.06
    omatic
    -0.06
    POSITIVE LOGITS
    icle
    0.14
    icles
    0.13
    law
    0.12
    iche
    0.11
     STORY
    0.11
     Slut
    0.11
     carc
    0.11
    ed
    0.11
    edriver
    0.11
    adas
    0.11
    Activations Density 0.003%

    No Known Activations