© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    sub- prefixes

    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
     laure
    -0.10
    REA
    -0.10
     quint
    -0.10
    hue
    -0.09
    apollo
    -0.09
     nack
    -0.09
     multinational
    -0.09
    STALL
    -0.09
    adder
    -0.09
    ATOR
    -0.08
    POSITIVE LOGITS
     minded
    0.11
    /sl
    0.11
     submissive
    0.10
     susceptible
    0.10
    shipping
    0.10
    bing
    0.10
    side
    0.10
     innocent
    0.10
    missive
    0.10
     obedience
    0.10
    Activations Density 0.003%

    No Known Activations