© 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. 16791
    Prev
    Next
    INDEX
    Explanations

    warning of negative outcomes

    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
     invis
    -0.11
     sexist
    -0.09
    athe
    -0.09
     Pride
    -0.09
     Denied
    -0.09
     insiders
    -0.09
     pride
    -0.09
     compartment
    -0.09
    _manifest
    -0.09
     +#
    -0.09
    POSITIVE LOGITS
     scare
    0.45
     scares
    0.37
     panic
    0.34
     scared
    0.34
     fear
    0.32
     fright
    0.32
     frightened
    0.32
     fears
    0.30
     Fear
    0.29
     scary
    0.29
    Activations Density 0.228%

    No Known Activations