© 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. 90232
    Prev
    Next
    INDEX
    Explanations

    Jimmy + surname

    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
    aan
    -0.12
    arge
    -0.11
    ary
    -0.10
    sz
    -0.10
    ilder
    -0.09
    ãĤį
    -0.09
    enu
    -0.09
    andom
    -0.08
    iac
    -0.08
     guts
    -0.08
    POSITIVE LOGITS
    tam
    0.10
     tamp
    0.09
     durante
    0.09
    enez
    0.09
    asca
    0.09
     Sly
    0.09
    ización
    0.08
    opard
    0.08
     incor
    0.08
    olest
    0.08
    Activations Density 0.011%

    No Known Activations