© 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. 25720
    Prev
    Next
    INDEX
    Explanations

    themed individual items, characters, or events

    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
    _multiple
    -0.11
    455
    -0.10
     dov
    -0.10
    _ser
    -0.10
    hee
    -0.10
    atee
    -0.10
    rug
    -0.10
     invalidated
    -0.10
    ipse
    -0.10
    ,default
    -0.10
    POSITIVE LOGITS
     themed
    0.21
     corresponding
    0.19
     different
    0.17
     each
    0.15
    each
    0.14
     thematic
    0.14
     unique
    0.14
     various
    0.14
     Each
    0.14
     varied
    0.14
    Activations Density 0.485%

    No Known Activations