© 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. 46356
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    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
     accurately
    -0.12
     smoothly
    -0.11
     effectively
    -0.11
     correctly
    -0.11
     into
    -0.11
     prominently
    -0.10
     adequately
    -0.10
    ENTA
    -0.10
    graphic
    -0.09
     faithfully
    -0.09
    POSITIVE LOGITS
     lest
    0.11
    ihan
    0.10
    itz
    0.10
    ret
    0.09
     ende
    0.09
    _WS
    0.09
     lately
    0.09
     tat
    0.09
    Singleton
    0.09
    atan
    0.09
    Activations Density 0.569%

    No Known Activations