© 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. 33380
    Prev
    Next
    INDEX
    Explanations

    reasons or excuses

    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
    lua
    -0.11
     licence
    -0.10
     reasoned
    -0.10
     invitation
    -0.10
    invitation
    -0.10
     bree
    -0.10
     pob
    -0.10
    tent
    -0.10
     license
    -0.10
    emo
    -0.10
    POSITIVE LOGITS
     why
    0.23
    why
    0.18
     Why
    0.14
     pourquoi
    0.13
    Why
    0.13
     WHY
    0.12
    "Why
    0.09
     ways
    0.08
    ABL
    0.08
     Shirley
    0.08
    Activations Density 0.006%

    No Known Activations