© 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. 4562
    Prev
    Next
    INDEX
    Explanations

    title, Professor, legends, membership

    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
    urr
    -0.08
     {{{
    -0.07
     happiest
    -0.07
    ìĥĿ
    -0.07
    _US
    -0.07
     ballo
    -0.07
     clas
    -0.07
    IVAL
    -0.07
     Edu
    -0.07
    sembl
    -0.07
    POSITIVE LOGITS
    etto
    0.13
    ?
    0.12
    iously
    0.12
    !
    0.11
    oubtedly
    0.11
    ardo
    0.10
    mente
    0.10
     Chad
    0.10
    iga
    0.10
    quartered
    0.10
    Activations Density 0.031%

    No Known Activations