© 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. 25597
    Prev
    Next
    INDEX
    Explanations

    a its

    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
    astes
    -0.09
     context
    -0.08
     pinch
    -0.08
     stopping
    -0.08
    703
    -0.08
    bil
    -0.08
    paid
    -0.08
     indis
    -0.08
    aba
    -0.07
    eni
    -0.07
    POSITIVE LOGITS
     entire
    0.15
     heck
    0.12
     Entire
    0.11
     interiors
    0.10
     citiz
    0.10
     resc
    0.10
     weary
    0.10
    Contours
    0.10
     Lad
    0.10
     Overs
    0.10
    Activations Density 0.385%

    No Known Activations