© 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. 115554
    Prev
    Next
    INDEX
    Explanations

    jer starts words like jerks, Jerusalem, Jeremy, Jeremiah

    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
    aurus
    -0.12
    e
    -0.10
    nable
    -0.09
    lä
    -0.09
    eres
    -0.09
    rons
    -0.08
    eren
    -0.08
    cala
    -0.08
     narrow
    -0.08
    cle
    -0.08
    POSITIVE LOGITS
     jer
    0.16
     jerk
    0.12
    jer
    0.12
    ôme
    0.12
    usal
    0.11
    face
    0.11
    /id
    0.11
    byn
    0.11
     chicken
    0.10
    boa
    0.10
    Activations Density 0.003%

    No Known Activations