© 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. 14315
    Prev
    Next
    INDEX
    Explanations

    Risk and danger

    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
     arsen
    -0.10
     deb
    -0.09
     unreachable
    -0.08
    org
    -0.08
     injust
    -0.08
    lein
    -0.08
    Org
    -0.07
     valid
    -0.07
     org
    -0.07
     massac
    -0.07
    POSITIVE LOGITS
     Unsafe
    0.17
     hazard
    0.16
     hazards
    0.15
     unsafe
    0.15
     peril
    0.15
    Risk
    0.15
     exposure
    0.14
     dangerous
    0.14
     danger
    0.14
     dangers
    0.14
    Activations Density 0.158%

    No Known Activations