© 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. 112665
    Prev
    Next
    INDEX
    Explanations

    names from Greece or Finland

    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
    à¹Į
    -0.12
     sill
    -0.11
     rude
    -0.10
    ↵      ↵
    -0.09
    ieur
    -0.09
     Dien
    -0.09
    .cms
    -0.09
     proceeds
    -0.09
    allee
    -0.09
    rir
    -0.09
    POSITIVE LOGITS
     pec
    0.09
     Behind
    0.08
    _compile
    0.08
     behind
    0.07
     gra
    0.07
    pson
    0.07
    .HttpServletResponse
    0.07
    /Web
    0.07
     WR
    0.07
    ám
    0.07
    Activations Density 0.322%

    No Known Activations