© 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. 90361
    Prev
    Next
    INDEX
    Explanations

    shopping, views, surprising, Thursday, Hood

    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
     Cities
    -0.13
    uzzi
    -0.12
    altar
    -0.12
     Glas
    -0.11
    çº
    -0.11
    ouch
    -0.11
     deficiencies
    -0.11
     Veronica
    -0.11
    Trust
    -0.11
    trust
    -0.11
    POSITIVE LOGITS
     crib
    0.07
     rem
    0.07
     Misc
    0.07
     anc
    0.06
    enge
    0.06
     Mort
    0.06
     periodically
    0.06
    onis
    0.06
     avis
    0.06
     misc
    0.06
    Activations Density 0.001%

    No Known Activations