© 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. 92140
    Prev
    Next
    INDEX
    Explanations

    try something today

    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
     unsuccessfully
    -0.13
     attempts
    -0.13
     attempted
    -0.13
     attempting
    -0.12
    anza
    -0.11
     trying
    -0.11
    _rw
    -0.11
     Trying
    -0.11
    otti
    -0.11
    Trying
    -0.11
    POSITIVE LOGITS
     sometime
    0.10
     Yourself
    0.09
     bloody
    0.08
     excell
    0.08
     satisfaction
    0.08
     betr
    0.08
    /by
    0.08
    aller
    0.08
     service
    0.08
    ales
    0.08
    Activations Density 0.050%

    No Known Activations