© 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. 48567
    Prev
    Next
    INDEX
    Explanations

    scribe, ninja, blo, ms, @, mming, fest

    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
     hitch
    -0.09
    vod
    -0.09
     Bee
    -0.08
     rop
    -0.08
    witter
    -0.08
     collectively
    -0.08
     Oro
    -0.08
     complicated
    -0.07
     italic
    -0.07
    anganese
    -0.07
    POSITIVE LOGITS
    Extras
    0.11
     whereby
    0.10
     darling
    0.09
    Jones
    0.09
     extras
    0.09
     Darling
    0.09
    ypse
    0.09
     cognition
    0.09
    FX
    0.09
    extras
    0.09
    Activations Density 0.161%

    No Known Activations