© 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. 115216
    Prev
    Next
    INDEX
    Explanations

    dialogue or response markers

    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
     ort
    -0.09
    ê±°
    -0.08
     noisy
    -0.08
    phrase
    -0.08
    hort
    -0.08
    "After
    -0.08
     thoroughly
    -0.08
    FT
    -0.08
     twitch
    -0.08
    089
    -0.08
    POSITIVE LOGITS
     replies
    0.17
     replied
    0.16
     reply
    0.15
     responses
    0.15
     Replies
    0.15
    “Well
    0.14
    "Well
    0.14
    "Yeah
    0.14
     responded
    0.13
     response
    0.13
    Activations Density 0.069%

    No Known Activations