© 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. 26673
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    /St
    -0.11
    abal
    -0.09
     Bent
    -0.09
     II
    -0.08
     Griff
    -0.08
     im
    -0.08
     decre
    -0.07
     intervening
    -0.07
     Admir
    -0.07
     BITS
    -0.07
    POSITIVE LOGITS
    ë²Ī
    0.16
    âĢ³
    0.15
    ï¸ı
    0.14
    apr
    0.10
    ³³³³
    0.10
    ³³³
    0.10
     Ping
    0.10
     Rex
    0.10
    âĢ²
    0.10
    ìŀ¥
    0.10
    Activations Density 0.257%

    No Known Activations