© 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. 27940
    Prev
    Next
    INDEX
    Explanations

    facial expressions

    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
     misd
    -0.13
     Blind
    -0.11
     McCabe
    -0.11
     dür
    -0.11
    tet
    -0.11
     lassen
    -0.11
     Cummings
    -0.11
    /left
    -0.10
     mans
    -0.10
    -expand
    -0.10
    POSITIVE LOGITS
    less
    0.09
     Sew
    0.09
     anx
    0.08
     anxiety
    0.08
    agos
    0.08
    shot
    0.08
     close
    0.08
     full
    0.08
     above
    0.08
     Wool
    0.08
    Activations Density 0.002%

    No Known Activations