© 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. 47808
    Prev
    Next
    INDEX
    Explanations

    called, named, termed, designated

    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
     tons
    -0.09
     harness
    -0.08
    érc
    -0.08
    otty
    -0.08
    endors
    -0.07
     Beginning
    -0.07
    Domain
    -0.07
    NotFound
    -0.07
     Thi
    -0.07
    downloads
    -0.07
    POSITIVE LOGITS
    称
    0.15
     termed
    0.11
    isson
    0.10
     designated
    0.10
     surely
    0.10
     collectively
    0.10
    ?)
    0.10
    term
    0.10
     term
    0.10
    ripper
    0.10
    Activations Density 0.093%

    No Known Activations