© 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. 50901
    Prev
    Next
    INDEX
    Explanations

    configuration file

    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
     [âĢ¦]↵↵
    -0.16
    [âĢ¦
    -0.13
    <|fim_suffix|>
    -0.13
     [âĢ¦
    -0.12
     [...]↵↵
    -0.10
    Âł
    -0.09
    Continue
    -0.09
     ...↵
    -0.08
     [âĢ¦]
    -0.08
     [...]
    -0.08
    POSITIVE LOGITS
     (!!
    0.11
    /Dk
    0.11
    )?.
    0.11
    ?).
    0.11
    IFn
    0.11
     Swal
    0.11
    isNew
    0.11
    -footer
    0.11
     Swinger
    0.10
    !!)↵
    0.10
    Activations Density 0.104%

    No Known Activations