© 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. 28998
    Prev
    Next
    INDEX
    Explanations

    stable / able

    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
    acy
    -0.11
    unky
    -0.10
    ables
    -0.10
     beware
    -0.09
    fulness
    -0.09
    /io
    -0.09
    sale
    -0.09
     kettle
    -0.09
    arat
    -0.09
     conven
    -0.09
    POSITIVE LOGITS
    coins
    0.16
    coin
    0.13
    ford
    0.11
    -minded
    0.11
    st
    0.11
     minded
    0.10
     foam
    0.10
     fool
    0.10
    kee
    0.10
    lector
    0.10
    Activations Density 0.064%

    No Known Activations