© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113939
    Prev
    Next
    INDEX
    Explanations

    DTD XHTML

    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
     Bij
    -0.13
     Rao
    -0.12
     weave
    -0.10
     Loft
    -0.10
    Het
    -0.10
     Rug
    -0.10
    kins
    -0.10
     Sloan
    -0.10
    ourke
    -0.10
     Rash
    -0.10
    POSITIVE LOGITS
    sville
    0.10
    ANTE
    0.08
     Witt
    0.08
     tonight
    0.07
     petite
    0.07
     bypass
    0.07
     fulfillment
    0.07
    getting
    0.07
     sequ
    0.07
     Pel
    0.07
    Activations Density 0.002%

    No Known Activations