© 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. 117083
    Prev
    Next
    INDEX
    Explanations

    completeness or high degree

    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
     slightly
    -0.13
     mildly
    -0.12
     somewhat
    -0.11
    ç¨į
    -0.10
     urgently
    -0.10
     moderately
    -0.09
     pinnacle
    -0.09
    ily
    -0.09
     richer
    -0.09
     slugg
    -0.09
    POSITIVE LOGITS
     devoid
    0.16
     completely
    0.15
     overshadow
    0.14
     unaware
    0.13
     entirely
    0.13
     unrelated
    0.12
     Completely
    0.12
     eclips
    0.12
     engulf
    0.12
     oblivious
    0.12
    Activations Density 0.097%

    No Known Activations