© 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. 90346
    Prev
    Next
    INDEX
    Explanations

    jefferson or jeffrey

    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
    nob
    -0.09
    hev
    -0.09
    ALLY
    -0.08
    ansible
    -0.08
     ache
    -0.08
     agency
    -0.08
    edin
    -0.08
    achable
    -0.07
    osa
    -0.07
    Ãłi
    -0.07
    POSITIVE LOGITS
    rey
    0.19
    ery
    0.18
    coat
    0.18
    ry
    0.15
    ords
    0.14
    ERY
    0.13
    ory
    0.12
    erson
    0.12
    ries
    0.12
    ree
    0.12
    Activations Density 0.012%

    No Known Activations