© 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. 5909
    Prev
    Next
    INDEX
    Explanations

    closing quotation followed by sentence start

    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
    —if
    -0.09
     Say
    -0.09
    /or
    -0.09
    /b
    -0.09
    -b
    -0.09
    /be
    -0.08
     Fem
    -0.08
     ‘
    -0.08
     Mens
    -0.08
    ä¿®
    -0.08
    POSITIVE LOGITS
    Â
    0.13
     Again
    0.12
     Their
    0.12
     This
    0.12
     Somehow
    0.11
     It
    0.11
     Armed
    0.11
     puff
    0.11
     There
    0.11
     hmm
    0.11
    Activations Density 0.022%

    No Known Activations