© 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. 17511
    Prev
    Next
    INDEX
    Explanations

    .NET development technologies

    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
     Dw
    -0.11
     wild
    -0.10
     complain
    -0.10
    wis
    -0.10
     reporter
    -0.10
    tex
    -0.10
     Reported
    -0.10
     rooting
    -0.10
     Pike
    -0.10
     Dawn
    -0.10
    POSITIVE LOGITS
    obble
    0.08
    swick
    0.07
    ILT
    0.07
    ubber
    0.07
     caste
    0.07
     Colony
    0.07
    roud
    0.07
    567
    0.07
    prung
    0.07
     Lie
    0.07
    Activations Density 0.010%

    No Known Activations