© 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. 88044
    Prev
    Next
    INDEX
    Explanations

    flat, low, small, or weak physical descriptions

    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
     bare
    -0.09
     Bare
    -0.08
    hands
    -0.08
     completeness
    -0.08
    ce
    -0.08
     cells
    -0.08
    andelier
    -0.08
     gord
    -0.08
     BAR
    -0.08
     plants
    -0.08
    POSITIVE LOGITS
     waist
    0.13
     stomach
    0.13
     abdomen
    0.12
     intervening
    0.11
     Waist
    0.11
     hips
    0.11
     Belly
    0.10
     belly
    0.10
    /address
    0.10
    -ish
    0.10
    Activations Density 0.007%

    No Known Activations