© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113234
    Prev
    Next
    INDEX
    Explanations

    contrast, however

    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
    __[
    -0.10
    ä¿
    -0.10
     darn
    -0.09
     Thorn
    -0.09
     anyway
    -0.09
     respectively
    -0.09
     stav
    -0.09
     they
    -0.09
     THREAD
    -0.09
    yne
    -0.09
    POSITIVE LOGITS
     has
    0.11
    have
    0.10
    AO
    0.10
    ,is
    0.10
     is
    0.10
     cannot
    0.09
     whose
    0.09
     have
    0.09
     who
    0.09
    rale
    0.09
    Activations Density 0.060%

    No Known Activations