© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90577
    Prev
    Next
    INDEX
    Explanations

    words starting with Ant

    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
     striking
    -0.09
    unate
    -0.08
     ly
    -0.08
    ging
    -0.08
    ready
    -0.08
     Caucasian
    -0.08
     ready
    -0.08
    orative
    -0.08
    atif
    -0.08
    ÑĤиÑĢов
    -0.07
    POSITIVE LOGITS
     Ant
    0.11
     Planned
    0.11
    ón
    0.11
    sat
    0.11
    он
    0.11
    icipation
    0.11
    conc
    0.10
     preview
    0.10
    je
    0.10
    iqu
    0.10
    Activations Density 0.026%

    No Known Activations