© 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. 32476
    Prev
    Next
    INDEX
    Explanations

    associated with, here are, representing ebikes, immunisation coverage

    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
     qed
    -0.11
     Sidebar
    -0.09
    elm
    -0.09
    sta
    -0.08
     kre
    -0.08
    uib
    -0.08
     kit
    -0.08
     Gambling
    -0.08
    agua
    -0.08
    OTP
    -0.08
    POSITIVE LOGITS
    -Length
    0.10
    closure
    0.10
     Audit
    0.09
     Greens
    0.09
    _|
    0.09
     coff
    0.09
    .BL
    0.09
     chambers
    0.09
    rait
    0.09
    Await
    0.09
    Activations Density 0.017%

    No Known Activations