© 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. 91735
    Prev
    Next
    INDEX
    Explanations

    reporting speech after quotes

    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
     immediately
    -0.13
     instantly
    -0.12
     promptly
    -0.12
     Immediately
    -0.10
     surprises
    -0.10
     joke
    -0.10
     disclosed
    -0.10
     casually
    -0.09
     presum
    -0.09
     Packs
    -0.09
    POSITIVE LOGITS
     repeated
    0.50
     repeating
    0.47
     repetition
    0.46
     repeats
    0.46
     repeat
    0.45
     repet
    0.43
     repetitive
    0.42
     repetitions
    0.39
     Repeat
    0.38
    repeat
    0.38
    Activations Density 0.035%

    No Known Activations