© 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. 7281
    Prev
    Next
    INDEX
    Explanations

    names and copyright notices

    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
     equiv
    -0.10
    ogui
    -0.10
     compr
    -0.10
     Mime
    -0.09
     Erotik
    -0.08
     mz
    -0.08
    %H
    -0.08
    ouri
    -0.08
    >čč↵
    -0.08
    \ORM
    -0.08
    POSITIVE LOGITS
     setSupportActionBar
    0.12
    ANI
    0.08
    .realm
    0.08
    /**<
    0.08
    figcaption
    0.07
    _bulk
    0.07
     manos
    0.07
    divider
    0.07
    DefaultCloseOperation
    0.07
     cram
    0.07
    Activations Density 3.097%

    No Known Activations