© 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. 47680
    Prev
    Next
    INDEX
    Explanations

    names following Jack

    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
    Ñİ
    -0.10
    seau
    -0.10
    lander
    -0.10
    cribe
    -0.10
     Picker
    -0.09
    sek
    -0.09
    isateur
    -0.09
    semb
    -0.09
        ↵    ↵    ↵
    -0.09
    regist
    -0.09
    POSITIVE LOGITS
    knife
    0.14
    dish
    0.12
    rabbit
    0.11
    nowled
    0.11
    pot
    0.11
    o
    0.10
    intosh
    0.10
    fruit
    0.10
    y
    0.10
    ey
    0.10
    Activations Density 0.011%

    No Known Activations