© 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. 26254
    Prev
    Next
    INDEX
    Explanations

    PLEASE, Warning, NOT, ONLY

    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
    ?,↵
    -0.12
     TOUCH
    -0.11
     PARTICULAR
    -0.11
     (?
    -0.11
    ienne
    -0.11
    .`,↵
    -0.10
     SCALE
    -0.10
    uml
    -0.10
    ignon
    -0.10
    enos
    -0.10
    POSITIVE LOGITS
     ONLY
    0.13
    PLEASE
    0.13
     please
    0.11
     PLEASE
    0.11
     beware
    0.11
    !!!
    0.11
     Warning
    0.11
     warning
    0.10
     Please
    0.10
     NOT
    0.10
    Activations Density 0.159%

    No Known Activations