© 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. 32166
    Prev
    Next
    INDEX
    Explanations

    Jim followed by last name

    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
     strict
    -0.09
    Strict
    -0.09
    ectomy
    -0.09
    HIP
    -0.09
    tsky
    -0.09
    appe
    -0.09
    ạn
    -0.09
     conspicuous
    -0.08
    essler
    -0.08
    ses
    -0.08
    POSITIVE LOGITS
    enez
    0.25
    mie
    0.18
    bo
    0.16
    mys
    0.14
    inez
    0.14
    i
    0.12
    othy
    0.12
    cat
    0.11
    blah
    0.11
    quisition
    0.11
    Activations Density 0.027%

    No Known Activations