© 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. 25479
    Prev
    Next
    INDEX
    Explanations

    whether you are in

    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
     explos
    -0.11
     Boom
    -0.11
    oir
    -0.11
    iot
    -0.11
     Chap
    -0.11
     Cli
    -0.11
    —including
    -0.10
    lus
    -0.10
     Boone
    -0.10
    /ex
    -0.10
    POSITIVE LOGITS
     Thorn
    0.08
     Kear
    0.08
     effected
    0.08
     Hick
    0.07
     aster
    0.07
    erer
    0.07
     Heller
    0.07
     gra
    0.07
     Kad
    0.07
    ·
    0.07
    Activations Density 0.022%

    No Known Activations