© 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. 14462
    Prev
    Next
    INDEX
    Explanations

    answering phones or calls

    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
     answer
    -0.15
    answer
    -0.13
     answered
    -0.13
     answering
    -0.13
     оÑĤвеÑĤ
    -0.12
     Answer
    -0.12
     Answers
    -0.12
     answers
    -0.12
    answers
    -0.12
    _answers
    -0.11
    POSITIVE LOGITS
    engu
    0.10
    bang
    0.10
    å¤Ħ
    0.10
    mlin
    0.09
    /store
    0.09
     reluct
    0.09
    edList
    0.09
     machines
    0.09
    /send
    0.09
     distress
    0.09
    Activations Density 0.005%

    No Known Activations