© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    email addresses

    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
     fung
    -0.12
     PyObject
    -0.10
     Teddy
    -0.10
    :]
    -0.10
     Ley
    -0.09
    ekyll
    -0.09
    æİĴ
    -0.09
    uby
    -0.09
     aster
    -0.09
    ertools
    -0.09
    POSITIVE LOGITS
     gmail
    0.18
    gmail
    0.15
    @gmail
    0.14
     outlook
    0.14
     Gmail
    0.13
     Outlook
    0.12
    .gmail
    0.10
     mail
    0.09
     Virgin
    0.09
    =out
    0.09
    Activations Density 0.030%

    No Known Activations