© 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. 32654
    Prev
    Next
    INDEX
    Explanations

    Apache License, Free, Copyright, contract, capsule

    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
     Hick
    -0.11
     kend
    -0.10
    ëĤ´
    -0.10
    ovel
    -0.10
    TEE
    -0.10
    rieb
    -0.10
    yne
    -0.10
     sparing
    -0.10
     mistr
    -0.10
     rematch
    -0.09
    POSITIVE LOGITS
    wand
    0.11
     altogether
    0.10
    ison
    0.10
    ka
    0.09
     entirely
    0.09
     completely
    0.09
    -Free
    0.09
     spraw
    0.09
    alto
    0.09
    FREE
    0.09
    Activations Density 0.003%

    No Known Activations