© 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. 15642
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
     oft
    -0.18
     decidedly
    -0.14
     foregoing
    -0.13
     requisite
    -0.13
     comparatively
    -0.12
     hoped
    -0.12
     admittedly
    -0.12
     disparate
    -0.11
     purely
    -0.11
     intervening
    -0.11
    POSITIVE LOGITS
    ones
    0.14
     meantime
    0.13
    ses
    0.12
     beginning
    0.12
     reason
    0.12
     amount
    0.12
     equipments
    0.12
    essian
    0.12
     abol
    0.12
    athers
    0.12
    Activations Density 0.333%

    No Known Activations