© 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. 31183
    Prev
    Next
    INDEX
    Explanations

    unfortunate outcome or statement

    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
     obviously
    -0.11
     Obviously
    -0.09
     filthy
    -0.09
     legitimately
    -0.09
     presumably
    -0.08
     anyway
    -0.08
     undoubtedly
    -0.08
    iero
    -0.08
    Obviously
    -0.08
     suicidal
    -0.07
    POSITIVE LOGITS
     disappointing
    0.31
     disappoint
    0.29
     unfortunately
    0.28
     sadly
    0.26
     disappointment
    0.25
     disappointed
    0.23
    Sadly
    0.22
     Unfortunately
    0.22
     Sadly
    0.21
     alas
    0.21
    Activations Density 0.359%

    No Known Activations