© 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. 112245
    Prev
    Next
    INDEX
    Explanations

    food items or parts of words

    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
     culmination
    -0.07
    ROUGH
    -0.07
    outed
    -0.07
    arily
    -0.07
    kan
    -0.07
     concerned
    -0.06
     pov
    -0.06
     wir
    -0.06
    ishly
    -0.06
    cheng
    -0.06
    POSITIVE LOGITS
     figur
    0.12
    afone
    0.12
    -awesome
    0.11
    FormatException
    0.11
    /movie
    0.11
     Weiner
    0.11
     ench
    0.10
     freaking
    0.10
     beware
    0.10
    epam
    0.10
    Activations Density 0.287%

    No Known Activations