© 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. 32819
    Prev
    Next
    INDEX
    Explanations

    sculptor or named person

    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
     bidi
    -0.12
     envelopes
    -0.12
     accordion
    -0.11
     gam
    -0.10
     Caj
    -0.10
     stew
    -0.10
    éĢĢ
    -0.10
    Envelope
    -0.10
     envelope
    -0.10
     polar
    -0.10
    POSITIVE LOGITS
     statue
    0.46
     sculpture
    0.44
     sculpt
    0.44
     sculptures
    0.42
     statues
    0.42
     Sculpt
    0.40
     Statue
    0.32
     carved
    0.32
     marble
    0.30
     carving
    0.29
    Activations Density 0.251%

    No Known Activations