© 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. 91622
    Prev
    Next
    INDEX
    Explanations

    not particularly

    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
     sept
    -0.11
    inx
    -0.11
     trom
    -0.11
     Wyn
    -0.10
    kok
    -0.10
     confidently
    -0.10
     Hacker
    -0.10
     Melanie
    -0.10
    643
    -0.10
     Rudd
    -0.10
    POSITIVE LOGITS
     flashy
    0.16
     excessively
    0.13
     overly
    0.13
     perfect
    0.12
     perfection
    0.11
     too
    0.11
     Corvette
    0.11
     fancy
    0.11
     excessive
    0.10
     loud
    0.10
    Activations Density 0.032%

    No Known Activations