© 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. 16221
    Prev
    Next
    INDEX
    Explanations

    faced, -faced, heid

    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
    sap
    -0.09
     fluffy
    -0.08
    gie
    -0.08
     BRO
    -0.08
     suger
    -0.08
     clipping
    -0.08
     Fond
    -0.08
     wig
    -0.08
     Silver
    -0.08
     cardio
    -0.08
    POSITIVE LOGITS
    -faced
    0.18
    ness
    0.13
    ed
    0.13
    face
    0.13
    keit
    0.11
    edBy
    0.11
    -face
    0.11
    heid
    0.11
     faced
    0.10
     billed
    0.09
    Activations Density 0.001%

    No Known Activations