© 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. 28125
    Prev
    Next
    INDEX
    Explanations

    highly + adjective

    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
     humble
    -0.10
    ruptcy
    -0.09
    ti
    -0.08
     shallow
    -0.08
    cie
    -0.08
     humility
    -0.08
    umba
    -0.08
     high
    -0.08
    handling
    -0.08
    ifier
    -0.08
    POSITIVE LOGITS
     regarded
    0.15
     unlikely
    0.13
    likely
    0.12
     visible
    0.12
     polished
    0.12
     recommend
    0.11
     rated
    0.11
     maneuver
    0.11
    -reg
    0.11
    -rated
    0.11
    Activations Density 0.031%

    No Known Activations