© 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. 90189
    Prev
    Next
    INDEX
    Explanations

    cheek, cheeks, face, -faced

    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
     uncomp
    -0.08
    idas
    -0.07
     unfamiliar
    -0.07
     Bark
    -0.07
    amar
    -0.06
    orta
    -0.06
     commod
    -0.06
     Fernando
    -0.06
    ải
    -0.06
    Whatever
    -0.06
    POSITIVE LOGITS
     cheek
    0.14
    y
    0.14
    face
    0.13
    -faced
    0.13
     flush
    0.13
    ed
    0.13
    FACE
    0.12
    yw
    0.12
    YG
    0.12
    -face
    0.12
    Activations Density 0.001%

    No Known Activations