© 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. 33612
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
     escap
    -0.11
     Dahl
    -0.10
     trot
    -0.10
    iting
    -0.10
     complic
    -0.10
     Revel
    -0.10
    arto
    -0.10
     dams
    -0.10
     frustr
    -0.10
     frustrating
    -0.10
    POSITIVE LOGITS
     nobody
    0.15
     smells
    0.12
    没æľī
    0.12
     smell
    0.11
     smelling
    0.11
     absence
    0.11
     why
    0.11
     theres
    0.10
     wears
    0.10
    Why
    0.10
    Activations Density 0.073%

    No Known Activations