© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16199
    Prev
    Next
    INDEX
    Explanations

    `such` language

    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
     invariably
    -0.09
    ãĥ³ãĥĪ
    -0.09
     discontin
    -0.09
     videot
    -0.08
     italiani
    -0.08
     Wid
    -0.08
     wid
    -0.08
     blocker
    -0.08
     aka
    -0.08
     fundamentally
    -0.08
    POSITIVE LOGITS
     thereof
    0.18
     such
    0.14
    such
    0.12
     accordingly
    0.11
     ones
    0.11
    et
    0.10
     SUCH
    0.10
    gil
    0.09
     ÑĤак
    0.09
    ãģĿ
    0.09
    Activations Density 0.290%

    No Known Activations