© 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. 113840
    Prev
    Next
    INDEX
    Explanations

    quotation marks and ellipses

    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
     ref
    -0.09
    uru
    -0.09
    uz
    -0.09
    onz
    -0.08
     Lounge
    -0.08
     job
    -0.08
    ache
    -0.08
     pron
    -0.08
     lounge
    -0.08
     Benz
    -0.08
    POSITIVE LOGITS
     “âĢ¦
    0.21
    âĢ¦the
    0.19
     “[
    0.17
     "...
    0.17
    âĢ¦it
    0.16
    (...)
    0.15
    QUOTE
    0.15
     "..
    0.15
     "[
    0.15
    [T
    0.15
    Activations Density 0.648%

    No Known Activations