© 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. 33794
    Prev
    Next
    INDEX
    Explanations

    body parts

    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
     mus
    -0.11
     Mos
    -0.09
    ucken
    -0.09
     unilateral
    -0.09
     Dixon
    -0.09
    -init
    -0.08
     Benn
    -0.08
    aggi
    -0.08
     bidi
    -0.08
    agg
    -0.08
    POSITIVE LOGITS
     portion
    0.21
     body
    0.19
     portions
    0.19
     part
    0.17
     shaft
    0.16
     Portions
    0.16
     parts
    0.16
     stalk
    0.16
     base
    0.16
     core
    0.15
    Activations Density 1.786%

    No Known Activations