© 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. 4271
    Prev
    Next
    INDEX
    Explanations

    height and physical size

    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
    hed
    -0.12
     Explosion
    -0.11
     dét
    -0.11
    /slick
    -0.10
     hardcore
    -0.10
    nk
    -0.10
    hone
    -0.10
    amo
    -0.10
     Hardcore
    -0.10
     Hed
    -0.10
    POSITIVE LOGITS
     height
    0.58
     taller
    0.55
     tallest
    0.52
     Height
    0.51
     heights
    0.51
     tall
    0.48
    Height
    0.48
    height
    0.45
    -height
    0.43
     Heights
    0.43
    Activations Density 0.310%

    No Known Activations