© 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. 28014
    Prev
    Next
    INDEX
    Explanations

    negative judgment or flawed actions

    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
     nomin
    -0.12
     Brun
    -0.12
     sharpen
    -0.11
     ingenious
    -0.11
     Thumbnails
    -0.11
     nominal
    -0.10
    oli
    -0.10
     Abr
    -0.10
     neutr
    -0.10
     skepticism
    -0.10
    POSITIVE LOGITS
     pathetic
    0.12
     betray
    0.11
     cond
    0.10
     ridiculous
    0.10
     capit
    0.10
     thinking
    0.10
     behaving
    0.10
    pak
    0.09
     gloss
    0.09
     lapse
    0.09
    Activations Density 0.024%

    No Known Activations