© 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. 18064
    Prev
    Next
    INDEX
    Explanations

    of

    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
     lon
    -0.09
    olin
    -0.09
     hind
    -0.09
     prosper
    -0.08
     contacted
    -0.08
     departing
    -0.08
     needy
    -0.08
     prosperous
    -0.08
     Cunning
    -0.08
     gathers
    -0.08
    POSITIVE LOGITS
     carb
    0.14
     conjug
    0.13
     binge
    0.12
     wearing
    0.12
     ordering
    0.11
    bib
    0.11
     fart
    0.10
     eating
    0.10
     Toe
    0.10
     Hair
    0.10
    Activations Density 0.793%

    No Known Activations