© 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. 48634
    Prev
    Next
    INDEX
    Explanations

    Share via e-mail

    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
     guild
    -0.09
    Phoenix
    -0.08
    bose
    -0.07
     Mills
    -0.07
     precip
    -0.07
    wear
    -0.07
     repar
    -0.07
     compensation
    -0.07
     compensated
    -0.07
     Cemetery
    -0.07
    POSITIVE LOGITS
    fty
    0.11
     Dort
    0.10
     Kra
    0.10
    aldo
    0.10
    CAF
    0.10
    ucken
    0.10
    ê¸
    0.10
    favorites
    0.10
     sidel
    0.10
    .news
    0.10
    Activations Density 0.002%

    No Known Activations