© 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. 16660
    Prev
    Next
    INDEX
    Explanations

    things not working or why

    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
     impulse
    -0.10
     wisely
    -0.10
     entirely
    -0.10
     withholding
    -0.08
    Privacy
    -0.08
     distraction
    -0.08
     stripping
    -0.08
    _ignore
    -0.08
    mez
    -0.08
     distr
    -0.08
    POSITIVE LOGITS
     frustrated
    0.24
     frustration
    0.24
     seemingly
    0.24
     frustrating
    0.24
     unsuccessful
    0.23
     struggle
    0.22
     struggling
    0.22
     frustrations
    0.22
     seem
    0.21
     struggles
    0.21
    Activations Density 0.716%

    No Known Activations