© 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. 115415
    Prev
    Next
    INDEX
    Explanations

    not having/feeling/knowing

    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
     mainstream
    -0.10
     realizing
    -0.10
     mundane
    -0.10
    URY
    -0.10
    orf
    -0.09
     realization
    -0.09
     rond
    -0.09
     backs
    -0.09
     animate
    -0.09
    tas
    -0.09
    POSITIVE LOGITS
     dare
    0.19
     Dare
    0.15
     dared
    0.14
     sure
    0.13
     confidence
    0.13
     feel
    0.12
     Confidence
    0.11
     feels
    0.11
     Feel
    0.11
    feel
    0.10
    Activations Density 0.091%

    No Known Activations