© 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. 91563
    Prev
    Next
    INDEX
    Explanations

    official declarations

    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
    illes
    -0.10
    onis
    -0.09
     Spicer
    -0.09
    èĢ
    -0.08
     Pepper
    -0.08
     Cousins
    -0.08
    eph
    -0.08
     aging
    -0.08
     pepper
    -0.07
     Hose
    -0.07
    POSITIVE LOGITS
     hereby
    0.55
     herein
    0.21
     declare
    0.21
     respectfully
    0.20
     shall
    0.19
     formally
    0.18
     officially
    0.18
     DECLARE
    0.18
     decree
    0.18
     solemn
    0.18
    Activations Density 1.177%

    No Known Activations