© 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. 88097
    Prev
    Next
    INDEX
    Explanations

    meaning and insight

    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
     acknowledged
    -0.11
     acknowledge
    -0.11
     acknowledgment
    -0.10
     acknowledgement
    -0.10
     ensured
    -0.10
     acknowledges
    -0.10
     ensuring
    -0.09
     urged
    -0.09
     encouraging
    -0.09
    Acknowled
    -0.09
    POSITIVE LOGITS
     revealing
    0.44
     reveals
    0.38
     reveal
    0.38
     clues
    0.38
     insight
    0.36
     Reve
    0.34
     insights
    0.33
     clue
    0.31
    reve
    0.30
     Insights
    0.30
    Activations Density 1.750%

    No Known Activations