© 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. 14347
    Prev
    Next
    INDEX
    Explanations

    wrong, err, decision, crazy

    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
    elic
    -0.12
     Tata
    -0.11
    иÑı
    -0.11
     disguised
    -0.11
    bite
    -0.11
     Prospect
    -0.11
    iya
    -0.11
    oto
    -0.11
    iele
    -0.11
    jh
    -0.11
    POSITIVE LOGITS
     bas
    0.08
     to
    0.08
     rag
    0.08
     baseline
    0.08
     by
    0.08
     shouldn
    0.08
    Ral
    0.07
    PIP
    0.07
     ditch
    0.07
     Quit
    0.07
    Activations Density 0.107%

    No Known Activations