© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14212
    Prev
    Next
    INDEX
    Explanations

    -iff / -ig / -ib / -izz

    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
    lä
    -0.10
    avar
    -0.09
     rake
    -0.08
     crush
    -0.08
    er
    -0.08
    eres
    -0.08
    Breadcrumb
    -0.08
    nings
    -0.08
    eken
    -0.08
     additionally
    -0.08
    POSITIVE LOGITS
    gle
    0.11
    adel
    0.11
    dos
    0.11
    ster
    0.11
    edBy
    0.10
    itty
    0.10
    keiten
    0.10
    ulin
    0.10
    pee
    0.10
    gy
    0.10
    Activations Density 0.021%

    No Known Activations