© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13905
    Prev
    Next
    INDEX
    Explanations

    United States District Court

    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
    Negative Logits
    ==>
    -0.10
    -0.09
    <|fim_suffix|>
    -0.08
    âĨĴ
    -0.08
    -->
    -0.07
    lest
    -0.07
     ''
    -0.07
    fare
    -0.07
     cas
    -0.07
    """↵↵↵
    -0.07
    POSITIVE LOGITS
     ***
    0.18
     *****
    0.17
    ******
    0.15
    -*
    0.15
    *****
    0.15
    ********
    0.15
    ***↵↵
    0.15
     aster
    0.14
    ~-~-~-~-
    0.14
     *↵↵
    0.14
    Activations Density 0.143%

    No Known Activations