© 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. 49730
    Prev
    Next
    INDEX
    Explanations

    numbers around 260 preceded by "No." or "Rv"

    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
     aw
    -0.08
    ÄĻ
    -0.08
     som
    -0.07
     Walton
    -0.07
     fierce
    -0.07
    ã
    -0.07
     garlic
    -0.07
    /non
    -0.07
     bass
    -0.07
    awa
    -0.07
    POSITIVE LOGITS
    stro
    0.11
     Teh
    0.11
     Tran
    0.10
    /connect
    0.10
     oa
    0.10
    abe
    0.10
     tease
    0.09
    aben
    0.09
    acre
    0.09
     Infinity
    0.09
    Activations Density 0.002%

    No Known Activations