© 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. 89393
    Prev
    Next
    INDEX
    Explanations

    personal feelings and desires

    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
    iad
    -0.12
     assumed
    -0.12
     bew
    -0.12
     scr
    -0.11
     understandably
    -0.11
    bew
    -0.10
     obviously
    -0.10
     tast
    -0.10
     rightfully
    -0.10
     assume
    -0.10
    POSITIVE LOGITS
     felt
    0.16
     feels
    0.15
     feel
    0.15
    Feel
    0.13
     WANT
    0.12
     desire
    0.12
    feel
    0.11
     Feel
    0.11
    felt
    0.11
     feeling
    0.10
    Activations Density 0.062%

    No Known Activations