© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90179
    Prev
    Next
    INDEX
    Explanations

    dealing with trouble or end

    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
     contempt
    -0.12
     Vend
    -0.11
    UTO
    -0.11
    437
    -0.10
    mast
    -0.10
    tero
    -0.10
     disappointment
    -0.10
     mast
    -0.09
     contamin
    -0.09
     fro
    -0.09
    POSITIVE LOGITS
     tame
    0.20
     beware
    0.17
     Bew
    0.17
     withstand
    0.16
     harness
    0.15
     Harness
    0.14
     coping
    0.14
     accommodating
    0.14
     cope
    0.14
     caution
    0.13
    Activations Density 0.202%

    No Known Activations