© 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. 4578
    Prev
    Next
    INDEX
    Explanations

    calls people

    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
     bystand
    -0.07
     alm
    -0.07
    wat
    -0.07
    Hal
    -0.06
     Harr
    -0.06
     mount
    -0.06
     Hal
    -0.06
     pointing
    -0.06
     Brass
    -0.06
    _priv
    -0.06
    POSITIVE LOGITS
     phone
    0.49
     telephone
    0.42
     call
    0.40
     calls
    0.40
     Phone
    0.40
     contacted
    0.39
     contact
    0.36
     contacting
    0.36
    phone
    0.35
    Phone
    0.35
    Activations Density 0.202%

    No Known Activations