© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32061
    Prev
    Next
    INDEX
    Explanations

    incomplete or trailing off

    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
    <|fim_prefix|>
    -0.09
     âĨĴ↵↵
    -0.09
    "\↵
    -0.09
    ↵
    -0.09
    <|fim_suffix|>
    -0.08
    Č↵
    -0.08
    !!!!↵↵
    -0.07
    !↵↵↵
    -0.07
    <|fim_middle|>
    -0.07
     [âĢ¦]↵↵
    -0.07
    POSITIVE LOGITS
    âĢ¦
    0.49
    ...
    0.47
     ...
    0.38
     âĢ¦
    0.38
    âĢ¦.
    0.35
    âĢ¦the
    0.34
    ..
    0.34
    ....
    0.33
    âĢ¦I
    0.32
     ..
    0.31
    Activations Density 0.136%

    No Known Activations