© 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. 32494
    Prev
    Next
    INDEX
    Explanations

    hey

    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
     singled
    -0.10
    /Index
    -0.10
    aison
    -0.10
     averaging
    -0.10
    ))*
    -0.09
     dak
    -0.09
     )*
    -0.09
    ful
    -0.09
     indexing
    -0.09
     Horny
    -0.09
    POSITIVE LOGITS
     Prest
    0.15
     prest
    0.14
     look
    0.12
     listen
    0.10
     lighten
    0.10
     don
    0.09
     maybe
    0.09
    Look
    0.09
    yyyy
    0.09
    HEY
    0.09
    Activations Density 0.006%

    No Known Activations