© 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. 26266
    Prev
    Next
    INDEX
    Explanations

    Lin or LINE

    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
    alah
    -0.11
     gle
    -0.10
    onna
    -0.09
    gens
    -0.09
     lifting
    -0.09
     sidel
    -0.09
     cher
    -0.09
     colourful
    -0.09
     elit
    -0.09
     shortcode
    -0.09
    POSITIVE LOGITS
     Lin
    0.14
     lin
    0.14
    Lin
    0.13
    .lin
    0.10
    lin
    0.10
     linen
    0.10
     nonlinear
    0.09
     bo
    0.09
     aw
    0.08
    LINE
    0.08
    Activations Density 0.098%

    No Known Activations