© 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. 116712
    Prev
    Next
    INDEX
    Explanations

    negative outcomes, risks, avoidance

    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
    eya
    -0.11
     otherwise
    -0.11
     Hatch
    -0.10
    modelo
    -0.10
     Kap
    -0.10
    otherwise
    -0.10
    åIJ¦
    -0.10
     lest
    -0.09
     OTHERWISE
    -0.09
     Otherwise
    -0.09
    POSITIVE LOGITS
     Worse
    0.19
     worse
    0.18
     avoided
    0.14
     worst
    0.14
     undesirable
    0.13
     therefore
    0.13
     risk
    0.13
     stakes
    0.12
     risks
    0.12
     avoidance
    0.12
    Activations Density 0.197%

    No Known Activations