© 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. 25347
    Prev
    Next
    INDEX
    Explanations

    facial expression

    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
    holds
    -0.10
     breakpoint
    -0.09
     conj
    -0.09
     zeal
    -0.09
    amo
    -0.08
    ’es
    -0.08
     unzip
    -0.08
    -gray
    -0.08
    -leaning
    -0.08
    abo
    -0.08
    POSITIVE LOGITS
     expressions
    0.13
     expression
    0.11
     Facial
    0.10
     expres
    0.10
    /body
    0.10
     stray
    0.10
    olle
    0.10
    lz
    0.10
    ly
    0.10
     cont
    0.10
    Activations Density 0.030%

    No Known Activations