© 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. 28540
    Prev
    Next
    INDEX
    Explanations

    saying nothing

    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
     Lehr
    -0.12
     outspoken
    -0.12
     genuinely
    -0.12
     joking
    -0.11
     irrespective
    -0.11
     brag
    -0.11
     neglect
    -0.11
     sincerely
    -0.10
    ll
    -0.10
     genuine
    -0.10
    POSITIVE LOGITS
     silently
    0.17
     tac
    0.15
     Suff
    0.14
     quietly
    0.14
     simply
    0.14
     suff
    0.13
     implicit
    0.12
     Implicit
    0.12
     implicitly
    0.12
     Silent
    0.11
    Activations Density 0.037%

    No Known Activations