© 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. 115597
    Prev
    Next
    INDEX
    Explanations

    scientific methods and mechanisms

    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
    Blake
    -0.10
     Rise
    -0.10
     ech
    -0.09
    irim
    -0.09
    ello
    -0.09
    arin
    -0.09
    869
    -0.09
    ŀĭ
    -0.08
     unlink
    -0.08
    phia
    -0.08
    POSITIVE LOGITS
     Bien
    0.11
    ysz
    0.09
    resa
    0.09
     Cherry
    0.08
    EXPORT
    0.08
    ogue
    0.08
    mith
    0.08
     standpoint
    0.08
    .Comm
    0.08
    HashCode
    0.08
    Activations Density 0.871%

    No Known Activations