© 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. 47382
    Prev
    Next
    INDEX
    Explanations

    danger and its forms

    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
    age
    -0.09
     goodwill
    -0.09
    ches
    -0.09
     Tent
    -0.09
     Piper
    -0.08
    parent
    -0.08
     tougher
    -0.08
    /MPL
    -0.08
    ernity
    -0.08
    vent
    -0.08
    POSITIVE LOGITS
    ous
    0.26
    ously
    0.26
     lur
    0.14
    osity
    0.14
    ousel
    0.13
    OUS
    0.13
     lurking
    0.13
     posed
    0.12
    rous
    0.12
     signs
    0.11
    Activations Density 0.037%

    No Known Activations