© 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. 88768
    Prev
    Next
    INDEX
    Explanations

    SHINE detector

    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
    linger
    -0.06
     sore
    -0.06
    OTES
    -0.06
    fe
    -0.06
     contracted
    -0.06
     Cad
    -0.06
     Dan
    -0.06
     tro
    -0.06
     Pare
    -0.06
    indo
    -0.06
    POSITIVE LOGITS
     Nicholson
    0.11
    (Un
    0.11
     går
    0.10
     Torres
    0.10
     adipiscing
    0.10
     Wilkinson
    0.10
     handjob
    0.10
    ï¼ı
    0.10
     Nutzung
    0.10
     prze
    0.10
    Activations Density 0.486%

    No Known Activations