© 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. 111787
    Prev
    Next
    INDEX
    Explanations

    got a / got you / got to

    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
    ek
    -0.08
     Gone
    -0.07
     gone
    -0.07
    gone
    -0.07
    -dominated
    -0.06
     roy
    -0.06
     grat
    -0.06
    ks
    -0.06
    led
    -0.06
    ised
    -0.06
    POSITIVE LOGITS
     Perkins
    0.12
    lä
    0.12
    sta
    0.12
    ixo
    0.12
     plenty
    0.11
     limitless
    0.11
    ovo
    0.11
     Barn
    0.11
    >čč↵
    0.11
    :hover
    0.11
    Activations Density 0.011%

    No Known Activations