© 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. 117031
    Prev
    Next
    INDEX
    Explanations

    action or movement description

    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
     retract
    -0.12
     fu
    -0.10
    ronics
    -0.10
    iline
    -0.10
    lix
    -0.09
    adoo
    -0.09
    abus
    -0.09
     distant
    -0.08
     welt
    -0.08
    IFS
    -0.08
    POSITIVE LOGITS
     headed
    0.12
     outgoing
    0.12
     Appearance
    0.11
     heading
    0.11
    appearance
    0.10
     appearance
    0.10
    Heading
    0.10
     whistle
    0.10
     swagger
    0.10
     departing
    0.09
    Activations Density 0.014%

    No Known Activations