© 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. 32533
    Prev
    Next
    INDEX
    Explanations

    show off legs

    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
     urg
    -0.12
    emean
    -0.10
    hom
    -0.10
     Twice
    -0.10
     desperation
    -0.10
     pup
    -0.09
    imas
    -0.09
     chew
    -0.09
     Masc
    -0.09
     strang
    -0.09
    POSITIVE LOGITS
     fla
    0.20
     showcase
    0.17
     showcasing
    0.17
     showcased
    0.17
     appreciation
    0.15
     showcases
    0.14
     Showcase
    0.14
     proudly
    0.14
     Fla
    0.14
     pride
    0.14
    Activations Density 0.034%

    No Known Activations