© 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. 112333
    Prev
    Next
    INDEX
    Explanations

    Sam followed by various endings

    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
    eger
    -0.11
        ↵    ↵
    -0.10
    esa
    -0.09
     fitted
    -0.09
    isse
    -0.09
     unh
    -0.08
     fancy
    -0.08
    imer
    -0.08
        ↵    ↵    ↵    ↵
    -0.08
        č↵
    -0.07
    POSITIVE LOGITS
    uels
    0.17
    plers
    0.17
    plings
    0.16
    urai
    0.15
    uel
    0.14
    wise
    0.14
    UEL
    0.13
    atha
    0.13
    stag
    0.13
    son
    0.13
    Activations Density 0.086%

    No Known Activations