© 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. 115841
    Prev
    Next
    INDEX
    Explanations

    technical and academic discussions

    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
     Exists
    -0.11
     Aires
    -0.11
     Loves
    -0.10
    uala
    -0.10
    onte
    -0.10
     Usa
    -0.09
    ieg
    -0.09
     hs
    -0.09
    sb
    -0.09
    ool
    -0.09
    POSITIVE LOGITS
     means
    0.19
     allows
    0.19
     requires
    0.19
     gives
    0.18
     brings
    0.18
     enables
    0.17
     makes
    0.17
     helps
    0.17
     reminds
    0.16
     resulted
    0.15
    Activations Density 0.269%

    No Known Activations