© 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. 115595
    Prev
    Next
    INDEX
    Explanations

    legal or technical documents

    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
     Downs
    -0.10
     Furn
    -0.10
     Macros
    -0.09
     fle
    -0.09
    PELL
    -0.09
     themselves
    -0.09
     Rosa
    -0.09
     bub
    -0.08
    ict
    -0.08
     Unt
    -0.08
    POSITIVE LOGITS
     Lambert
    0.10
    MESS
    0.10
    wen
    0.09
     volte
    0.09
     provoc
    0.09
     exh
    0.09
     exotic
    0.09
    izi
    0.09
    -u
    0.09
     weakening
    0.09
    Activations Density 0.103%

    No Known Activations