© 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. 115394
    Prev
    Next
    INDEX
    Explanations

    You followed by auxiliary verbs

    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
     ble
    -0.13
    enga
    -0.12
    à¹Į
    -0.11
    angi
    -0.11
    dsl
    -0.11
     bleach
    -0.11
    etti
    -0.11
     BLE
    -0.11
     penny
    -0.10
     Flo
    -0.10
    POSITIVE LOGITS
     Translator
    0.08
     Tamb
    0.08
    ERIC
    0.07
    ein
    0.07
     Should
    0.07
     should
    0.07
     Guaranteed
    0.07
    Must
    0.07
     Hd
    0.07
     thereby
    0.07
    Activations Density 0.040%

    No Known Activations