© 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. 91168
    Prev
    Next
    INDEX
    Explanations

    parts of the body consists

    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
    itational
    -0.09
     imminent
    -0.09
     lately
    -0.09
    omorphic
    -0.09
     Moran
    -0.08
     implies
    -0.08
    ire
    -0.08
    rang
    -0.08
    使
    -0.08
     Larson
    -0.08
    POSITIVE LOGITS
     consists
    0.19
     contains
    0.18
     contain
    0.16
     comprises
    0.16
     consist
    0.15
     undergo
    0.15
     Contains
    0.15
     acts
    0.14
     continuously
    0.14
     normally
    0.13
    Activations Density 1.253%

    No Known Activations