© 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. 28647
    Prev
    Next
    INDEX
    Explanations

    Medical conditions, Corporation, haircut, post

    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
    >({
    -0.10
    CSI
    -0.10
    .uni
    -0.10
    plat
    -0.10
    (SP
    -0.09
    <quote
    -0.09
     perpetr
    -0.09
     Franken
    -0.09
     Meyer
    -0.09
    oooooooo
    -0.09
    POSITIVE LOGITS
    @a
    0.06
    ataka
    0.05
     Firm
    0.05
    ..."↵
    0.05
    eus
    0.05
    vrir
    0.05
    gomery
    0.05
    ...↵
    0.05
    elah
    0.05
     Dor
    0.05
    Activations Density 5.940%

    No Known Activations