© 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. 46414
    Prev
    Next
    INDEX
    Explanations

    due in part

    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
    bor
    -0.10
    isco
    -0.09
    pery
    -0.09
    ugi
    -0.09
    ugg
    -0.08
     massively
    -0.08
    IDEO
    -0.08
    ,is
    -0.08
    adin
    -0.08
     Juice
    -0.08
    POSITIVE LOGITS
    à¹Į
    0.11
    Ìģ
    0.09
    Pont
    0.09
    pone
    0.09
    raud
    0.09
     slur
    0.08
    bib
    0.08
     Missing
    0.08
    Ľå»º
    0.08
    rema
    0.08
    Activations Density 0.149%

    No Known Activations