© 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. 5069
    Prev
    Next
    INDEX
    Explanations

    Russian text, sometimes garbled

    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
     Robbins
    -0.07
    LOS
    -0.07
     Missing
    -0.06
    asz
    -0.06
    hell
    -0.06
    ardu
    -0.05
    ity
    -0.05
    ittel
    -0.05
     Spl
    -0.05
     acqu
    -0.05
    POSITIVE LOGITS
    ãģı
    0.14
    ãĤī
    0.14
    른
    0.13
    ãĥ¼
    0.13
    äºĽ
    0.13
    ä¹Ī
    0.12
     Hats
    0.12
     systematically
    0.12
    è¾
    0.12
    ableObject
    0.12
    Activations Density 0.066%

    No Known Activations