© 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. 15688
    Prev
    Next
    INDEX
    Explanations

    distributed in the hope

    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
     Meer
    -0.09
    âĦ
    -0.08
     Princip
    -0.08
     manner
    -0.08
    ison
    -0.08
     questioned
    -0.07
     Concurrent
    -0.07
     proc
    -0.07
     Earn
    -0.07
     mere
    -0.07
    POSITIVE LOGITS
     willing
    0.14
     sure
    0.13
     passionate
    0.12
     constantly
    0.11
     likely
    0.11
     fascinated
    0.11
     accustomed
    0.11
     fiercely
    0.11
     incredibly
    0.10
     sympathetic
    0.10
    Activations Density 0.002%

    No Known Activations