© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26662
    Prev
    Next
    INDEX
    Explanations

    aw, ay, op, och

    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
     ret
    -0.08
     latter
    -0.08
     reconciliation
    -0.08
     expend
    -0.08
     past
    -0.08
     departure
    -0.07
     refriger
    -0.07
     prer
    -0.07
     congest
    -0.07
     départ
    -0.07
    POSITIVE LOGITS
    weit
    0.10
    Misc
    0.10
    aths
    0.10
    andin
    0.10
    wert
    0.10
    prt
    0.10
    arda
    0.10
    blast
    0.09
     Nina
    0.09
    apol
    0.09
    Activations Density 0.311%

    No Known Activations