© 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. 32811
    Prev
    Next
    INDEX
    Explanations

    em- starting words

    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
    changer
    -0.08
    icine
    -0.08
    ings
    -0.08
    tings
    -0.08
     Pun
    -0.07
    less
    -0.07
     Zur
    -0.07
     Trident
    -0.07
    eware
    -0.07
     scand
    -0.07
    POSITIVE LOGITS
    s
    0.16
    /em
    0.16
     em
    0.15
    ulators
    0.14
    ulsion
    0.13
    ulating
    0.13
    erald
    0.13
    sdk
    0.12
     emulator
    0.12
    /export
    0.12
    Activations Density 0.012%

    No Known Activations