© 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. 88557
    Prev
    Next
    INDEX
    Explanations

    menu, tab, cookies, jQuery, want

    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
    /stretch
    -0.11
     recoil
    -0.10
    istor
    -0.09
    lian
    -0.09
     Fay
    -0.09
     abdom
    -0.09
    /el
    -0.09
     jub
    -0.09
    bjerg
    -0.08
    DJ
    -0.08
    POSITIVE LOGITS
     handed
    0.10
    orne
    0.09
     laz
    0.09
    isu
    0.09
     handing
    0.09
     sic
    0.09
    acre
    0.09
     beep
    0.08
    USD
    0.08
    eria
    0.08
    Activations Density 0.010%

    No Known Activations