© 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. 32593
    Prev
    Next
    INDEX
    Explanations

    contextualizing negative situations

    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
    .Once
    -0.12
     unfortunately
    -0.11
     ë§
    -0.11
     Cata
    -0.10
     regret
    -0.10
     quickly
    -0.10
    /xml
    -0.10
    OLUTE
    -0.10
     usual
    -0.10
     szy
    -0.10
    POSITIVE LOGITS
     presumably
    0.21
     arguably
    0.20
     potentially
    0.19
     possibly
    0.18
     supposedly
    0.16
     probably
    0.16
     apparently
    0.15
     moreover
    0.15
     essentially
    0.15
     practically
    0.14
    Activations Density 0.215%

    No Known Activations