© 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. 30506
    Prev
    Next
    INDEX
    Explanations

    attention and important notes

    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
    æĮ
    -0.13
    iasi
    -0.13
    eo
    -0.11
     fil
    -0.11
     blessings
    -0.10
     employed
    -0.10
    owe
    -0.10
    een
    -0.10
    fh
    -0.10
    /detail
    -0.10
    POSITIVE LOGITS
     READ
    0.13
     read
    0.11
    READ
    0.11
     IMPORTANT
    0.11
    PLEASE
    0.10
     BEFORE
    0.10
    _read
    0.10
     !!!
    0.10
     PLEASE
    0.09
     Important
    0.09
    Activations Density 0.161%

    No Known Activations