© 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. 116011
    Prev
    Next
    INDEX
    Explanations

    make sure

    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
     tend
    -0.14
    may
    -0.13
     seem
    -0.12
     seemed
    -0.11
     MAY
    -0.11
    ieber
    -0.11
     Ãĸ
    -0.11
     tends
    -0.11
     may
    -0.10
    might
    -0.10
    POSITIVE LOGITS
     stays
    0.20
     stay
    0.17
     stayed
    0.14
     gets
    0.13
     remains
    0.13
     conforms
    0.12
     understand
    0.12
     understands
    0.12
     Stay
    0.12
     get
    0.11
    Activations Density 0.089%

    No Known Activations