© 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. 88968
    Prev
    Next
    INDEX
    Explanations

    tw followed by oper, ilio, ice, elfth, ister, inning

    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
    à¯įà®
    -0.10
     Slater
    -0.10
    ientes
    -0.10
    -import
    -0.10
     paran
    -0.10
    DataTable
    -0.10
    ensch
    -0.10
    amento
    -0.09
    arest
    -0.09
    éĶĻ
    -0.09
    POSITIVE LOGITS
    s
    0.16
    -thirds
    0.15
    isted
    0.11
    elfth
    0.11
    /th
    0.11
    nty
    0.10
    rch
    0.10
    nd
    0.10
     thirds
    0.10
    sip
    0.09
    Activations Density 0.003%

    No Known Activations