© 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. 31784
    Prev
    Next
    INDEX
    Explanations

    outward appearance or looks

    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
    icut
    -0.11
    undra
    -0.10
     authenticity
    -0.10
     sincerity
    -0.10
    laden
    -0.09
    atest
    -0.09
     Alonso
    -0.09
    agu
    -0.09
     authenticated
    -0.09
     Charm
    -0.09
    POSITIVE LOGITS
     appearance
    0.17
     appearances
    0.16
     size
    0.15
     exterior
    0.14
     stature
    0.14
     Appearance
    0.13
     looks
    0.13
     outward
    0.13
     small
    0.12
     dimin
    0.12
    Activations Density 0.066%

    No Known Activations