© 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. 48493
    Prev
    Next
    INDEX
    Explanations

    dates in 2007 or 2008

    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
    alk
    -0.11
     Raz
    -0.10
    (http
    -0.10
     blush
    -0.10
     Wor
    -0.09
     Viv
    -0.09
     Nev
    -0.09
     Incorporated
    -0.09
    itution
    -0.09
     Winter
    -0.09
    POSITIVE LOGITS
     FULL
    0.09
    -_
    0.09
     casualties
    0.08
     Floyd
    0.08
    oba
    0.08
     stalls
    0.08
    Weights
    0.07
    893
    0.07
     unre
    0.07
    )["
    0.07
    Activations Density 0.049%

    No Known Activations