© 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. 32793
    Prev
    Next
    INDEX
    Explanations

    so much / very much

    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
     Bare
    -0.09
     Hans
    -0.09
    Yahoo
    -0.09
     Glad
    -0.09
     garant
    -0.09
     Gand
    -0.08
     undeniable
    -0.08
    bare
    -0.08
    éd
    -0.08
    olicy
    -0.08
    POSITIVE LOGITS
     coder
    0.12
     Germ
    0.11
     warp
    0.10
     Warp
    0.10
     allot
    0.10
     Coins
    0.09
    --)
    0.09
     midway
    0.09
    irc
    0.09
    .tf
    0.08
    Activations Density 0.003%

    No Known Activations