© 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. 17006
    Prev
    Next
    INDEX
    Explanations

    want a / want to

    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
     Verd
    -0.13
    .Ver
    -0.13
     folks
    -0.11
     %"
    -0.10
    peg
    -0.10
     biz
    -0.10
    olls
    -0.10
    ker
    -0.10
    bast
    -0.10
     wink
    -0.10
    POSITIVE LOGITS
     refund
    0.13
     Coff
    0.10
     tang
    0.10
     live
    0.09
     slee
    0.08
    wald
    0.08
     Schw
    0.08
     Funding
    0.08
     numbered
    0.08
     nested
    0.08
    Activations Density 0.060%

    No Known Activations