© 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. 33300
    Prev
    Next
    INDEX
    Explanations

    positive feelings and experiences

    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
    oso
    -0.10
    olk
    -0.10
     ger
    -0.10
    aye
    -0.10
    sap
    -0.10
     Bark
    -0.10
    iben
    -0.09
     Spicer
    -0.09
    otor
    -0.09
    enen
    -0.09
    POSITIVE LOGITS
     feeling
    0.42
     Feeling
    0.31
     sensation
    0.30
     feelings
    0.27
     sensations
    0.22
     feels
    0.21
     feel
    0.21
     Feel
    0.20
    æĦŁ
    0.20
    feel
    0.18
    Activations Density 0.098%

    No Known Activations