© 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. 28551
    Prev
    Next
    INDEX
    Explanations

    smiling, laughing, happy

    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
     smiles
    -0.18
     smiled
    -0.17
     smile
    -0.15
     smiling
    -0.14
     Smile
    -0.13
    (sm
    -0.09
    .ylabel
    -0.09
    ylabel
    -0.09
     systemd
    -0.08
     sop
    -0.08
    POSITIVE LOGITS
    icho
    0.12
     Beetle
    0.12
     Sheridan
    0.12
    zan
    0.11
    reh
    0.11
     Phonetic
    0.11
     Pound
    0.11
    iltr
    0.11
    mts
    0.10
     Infect
    0.10
    Activations Density 0.071%

    No Known Activations