© 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. 17497
    Prev
    Next
    INDEX
    Explanations

    rank and relevance

    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
    atto
    -0.12
    å£
    -0.12
     UPDATED
    -0.11
    ftime
    -0.11
    quist
    -0.10
     burst
    -0.10
    Wnd
    -0.10
    -even
    -0.10
    nds
    -0.10
    uit
    -0.10
    POSITIVE LOGITS
    Eye
    0.09
     Lum
    0.07
     eye
    0.07
     Hair
    0.07
     Hol
    0.07
     fore
    0.07
     Holmes
    0.07
     Cran
    0.07
    vet
    0.07
    IMAL
    0.07
    Activations Density 0.002%

    No Known Activations