© 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. 49736
    Prev
    Next
    INDEX
    Explanations

    negation and potential 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
    oria
    -0.10
     stabil
    -0.10
    erville
    -0.10
     acknowledgement
    -0.10
     minimized
    -0.10
    iros
    -0.09
     pragma
    -0.09
     Fog
    -0.09
     Dunn
    -0.09
     satisfied
    -0.09
    POSITIVE LOGITS
     scientifically
    0.16
     conclus
    0.15
     dangerous
    0.13
     medically
    0.13
     magically
    0.13
     Dangerous
    0.13
     permanently
    0.12
     magical
    0.12
     harmful
    0.12
     proven
    0.11
    Activations Density 0.182%

    No Known Activations