© 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. 48141
    Prev
    Next
    INDEX
    Explanations

    if conditional

    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
    aval
    -0.11
    778
    -0.10
    Cheers
    -0.09
     sleeper
    -0.09
    indy
    -0.09
    edom
    -0.09
    elan
    -0.09
    KS
    -0.09
    744
    -0.09
     --------
    -0.09
    POSITIVE LOGITS
     means
    0.18
    means
    0.18
     Means
    0.17
    Means
    0.16
     thereby
    0.13
    _means
    0.11
     helps
    0.11
     guarantee
    0.11
     benefit
    0.11
     saving
    0.11
    Activations Density 0.137%

    No Known Activations