© 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. 32478
    Prev
    Next
    INDEX
    Explanations

    if or when conditions

    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
    rips
    -0.10
    iode
    -0.10
    iets
    -0.10
     unlucky
    -0.10
     marshal
    -0.09
     aust
    -0.09
     Niet
    -0.09
    pluck
    -0.09
     teardown
    -0.09
     POV
    -0.09
    POSITIVE LOGITS
     prompted
    0.16
     presented
    0.15
     offered
    0.15
     receives
    0.14
     encouraged
    0.14
     confronted
    0.13
     challenged
    0.13
     receiving
    0.13
     reminded
    0.13
     pressured
    0.13
    Activations Density 0.196%

    No Known Activations