© 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. 88679
    Prev
    Next
    INDEX
    Explanations

    .com links and URL components

    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
     Sext
    -0.11
     Shr
    -0.10
     imaginable
    -0.09
     unr
    -0.09
     Ing
    -0.09
     Robbie
    -0.09
     Huck
    -0.09
     Vib
    -0.08
     Seth
    -0.08
     Eg
    -0.08
    POSITIVE LOGITS
     uid
    0.09
     waterfall
    0.09
     sabot
    0.08
    rig
    0.08
    hev
    0.08
    HP
    0.08
    IPA
    0.08
    THR
    0.08
     outright
    0.08
    rollo
    0.08
    Activations Density 0.004%

    No Known Activations