© 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. 88302
    Prev
    Next
    INDEX
    Explanations

    asking "how" or "what"

    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
    abe
    -0.08
    oval
    -0.08
     scattered
    -0.07
     unnoticed
    -0.07
     unt
    -0.07
    utter
    -0.07
    eo
    -0.07
    lets
    -0.07
    /me
    -0.07
     overhe
    -0.07
    POSITIVE LOGITS
    —are
    0.15
    ?,↵
    0.14
     denn
    0.14
    —is
    0.13
    æĺ¯åIJ¦
    0.13
     intend
    0.13
     WHY
    0.12
     intends
    0.12
     WHETHER
    0.12
     Why
    0.12
    Activations Density 0.161%

    No Known Activations