© 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. 28086
    Prev
    Next
    INDEX
    Explanations

    explaining a reason

    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
     lest
    -0.10
    -it
    -0.10
     tie
    -0.09
    Bow
    -0.09
    chr
    -0.09
    882
    -0.09
    unt
    -0.09
     hadn
    -0.09
     Picker
    -0.09
    there
    -0.08
    POSITIVE LOGITS
    iest
    0.11
     Arcade
    0.09
    /met
    0.09
     Belmont
    0.09
     instrumental
    0.09
     :=↵
    0.08
    ertest
    0.08
    Compat
    0.08
     UPS
    0.08
    noinspection
    0.08
    Activations Density 0.060%

    No Known Activations