© 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. 6179
    Prev
    Next
    INDEX
    Explanations

    positive emotional response

    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
    bol
    -0.10
     tol
    -0.09
     Catal
    -0.09
    ZX
    -0.09
    agne
    -0.08
    agg
    -0.08
    çIJ
    -0.08
     bol
    -0.08
     Bentley
    -0.08
    alan
    -0.08
    POSITIVE LOGITS
     every
    0.14
    every
    0.12
     grind
    0.11
    rier
    0.10
     sip
    0.10
     Every
    0.10
    lap
    0.10
     glorious
    0.09
     pii
    0.09
    iar
    0.09
    Activations Density 0.037%

    No Known Activations