© 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. 91815
    Prev
    Next
    INDEX
    Explanations

    body shapes and proportions

    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
     louder
    -0.11
     Beard
    -0.10
     neigh
    -0.10
     microscopic
    -0.10
     Behaviour
    -0.10
     coloured
    -0.10
     spont
    -0.10
    -white
    -0.10
     colourful
    -0.10
     blinds
    -0.10
    POSITIVE LOGITS
     shape
    0.23
     hips
    0.23
     taper
    0.20
     shoulders
    0.20
    shape
    0.19
     torso
    0.18
     waist
    0.18
     Shape
    0.17
     thighs
    0.17
     shapes
    0.17
    Activations Density 0.047%

    No Known Activations