© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32060
    Prev
    Next
    INDEX
    Explanations

    bleeding, bleachy, bleats, bleak

    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
     rightful
    -0.08
    ALAR
    -0.08
     striking
    -0.08
     embell
    -0.08
     peoples
    -0.08
    olis
    -0.07
     lessen
    -0.07
     rightfully
    -0.07
    nez
    -0.07
    ından
    -0.07
    POSITIVE LOGITS
     Ble
    0.14
    ibt
    0.13
     ble
    0.13
    eding
    0.13
    azard
    0.12
    isure
    0.12
     BLE
    0.12
    ached
    0.12
    edin
    0.11
    achers
    0.10
    Activations Density 0.031%

    No Known Activations