© 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. 46795
    Prev
    Next
    INDEX
    Explanations

    J names or initialisms

    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
     joints
    -0.11
     ins
    -0.10
     jazz
    -0.10
    ToJson
    -0.10
     joint
    -0.09
    ض
    -0.09
    Json
    -0.09
    _json
    -0.09
     jointly
    -0.08
     Schwe
    -0.08
    POSITIVE LOGITS
    (J
    0.15
    /J
    0.13
    .showMessageDialog
    0.13
    :j
    0.13
     ìķĬ
    0.12
    ernaut
    0.12
    =j
    0.11
    stice
    0.11
     Doe
    0.10
     sais
    0.10
    Activations Density 1.275%

    No Known Activations