© 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. 91602
    Prev
    Next
    INDEX
    Explanations

    es ... phage

    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
     Giov
    -0.09
    eron
    -0.09
    inh
    -0.09
    corp
    -0.09
    zon
    -0.09
    /doc
    -0.08
    o
    -0.08
     Balt
    -0.08
     Scr
    -0.08
    haven
    -0.08
    POSITIVE LOGITS
    oteric
    0.14
    ophage
    0.12
    pecially
    0.11
    SENT
    0.11
    sex
    0.10
     obsc
    0.10
    entially
    0.10
     ensuing
    0.09
     es
    0.09
    quo
    0.09
    Activations Density 0.032%

    No Known Activations