© 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. 88318
    Prev
    Next
    INDEX
    Explanations

    will... posted

    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
     afterward
    -0.09
     ready
    -0.09
    dd
    -0.09
     Goodman
    -0.09
     afterwards
    -0.08
     Fern
    -0.08
     worked
    -0.08
    adi
    -0.08
     Abb
    -0.08
     allegiance
    -0.08
    POSITIVE LOGITS
     will
    0.17
    will
    0.16
     WILL
    0.14
    ä¼ļ
    0.14
    ’ll
    0.14
     ill
    0.13
     Ill
    0.13
     Will
    0.13
    Will
    0.12
    'll
    0.12
    Activations Density 0.108%

    No Known Activations