© 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. 6759
    Prev
    Next
    INDEX
    Explanations

    causes 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
     Surprise
    -0.11
    reas
    -0.10
    ä¸įåŃĺåľ¨
    -0.10
    iske
    -0.09
     Bri
    -0.09
     unh
    -0.09
     Grinding
    -0.09
    coc
    -0.09
    anager
    -0.08
    altar
    -0.08
    POSITIVE LOGITS
     caused
    0.11
     reperc
    0.11
     mish
    0.11
     accidentally
    0.11
     spo
    0.11
     consequences
    0.10
     bore
    0.10
     gon
    0.10
     peril
    0.10
     chilled
    0.10
    Activations Density 0.069%

    No Known Activations