© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90069
    Prev
    Next
    INDEX
    Explanations

    entire body or area

    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
     prima
    -0.12
    /*/
    -0.11
     mod
    -0.11
    iest
    -0.11
    ponce
    -0.11
    ulary
    -0.11
    alt
    -0.10
     impass
    -0.10
    oba
    -0.10
     Contrast
    -0.10
    POSITIVE LOGITS
     entire
    0.23
     whole
    0.17
    æķ´
    0.16
     entirety
    0.14
     Entire
    0.14
     surrounding
    0.11
    whole
    0.11
     area
    0.11
     surface
    0.09
     related
    0.09
    Activations Density 0.102%

    No Known Activations