© 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. 113196
    Prev
    Next
    INDEX
    Explanations

    can be

    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
    uria
    -0.13
    ardon
    -0.10
     constantly
    -0.10
    sts
    -0.10
     persist
    -0.10
    inya
    -0.10
    itized
    -0.10
    STS
    -0.10
     circulating
    -0.10
     "'.
    -0.09
    POSITIVE LOGITS
     fun
    0.13
     rewarding
    0.12
     FUN
    0.12
     enjoyable
    0.11
     enrich
    0.11
     help
    0.11
     fruitful
    0.11
     invaluable
    0.10
    Fun
    0.10
     Fun
    0.10
    Activations Density 0.001%

    No Known Activations