© 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. 91512
    Prev
    Next
    INDEX
    Explanations

    channel subsystem

    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
    ---
    -0.11
    --
    -0.10
     representative
    -0.09
    nf
    -0.09
    ...
    -0.09
    odi
    -0.09
     observ
    -0.08
     overly
    -0.08
    pert
    -0.08
    æĴ
    -0.08
    POSITIVE LOGITS
     CZ
    0.13
     physique
    0.12
     Ebook
    0.12
     crimson
    0.12
     Whilst
    0.12
     lawful
    0.11
     nicely
    0.11
     ë¡
    0.11
    Whilst
    0.11
     chilly
    0.10
    Activations Density 0.224%

    No Known Activations