© 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. 30748
    Prev
    Next
    INDEX
    Explanations

    the noun

    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
    amber
    -0.09
     thereof
    -0.07
    elters
    -0.07
    ÃĤ
    -0.07
    â
    -0.07
    erot
    -0.07
    prot
    -0.07
    bris
    -0.07
    dde
    -0.07
     favorites
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.11
     attent
    0.11
     bulky
    0.11
     pes
    0.10
     NGO
    0.10
    /read
    0.10
     pricey
    0.10
     Mention
    0.10
     appe
    0.10
     afore
    0.10
    Activations Density 0.551%

    No Known Activations