© 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. 46903
    Prev
    Next
    INDEX
    Explanations

    inside/into body cavities

    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
    ads
    -0.10
     groom
    -0.09
    acket
    -0.08
    sten
    -0.08
     McDon
    -0.08
    ва
    -0.07
     Rath
    -0.07
    rik
    -0.07
    IGH
    -0.07
    ania
    -0.07
    POSITIVE LOGITS
     bodies
    0.25
     Bodies
    0.22
     body
    0.21
    -body
    0.19
     stomach
    0.19
    body
    0.18
    ä½ĵ
    0.18
     guts
    0.17
     intest
    0.17
     Body
    0.17
    Activations Density 0.261%

    No Known Activations