© 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. 5008
    Prev
    Next
    INDEX
    Explanations

    Hybrid, Create, Love, Possible, Are, My

    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
    gee
    -0.09
     Tot
    -0.07
     tot
    -0.07
    erm
    -0.07
     capitals
    -0.07
     Verb
    -0.07
    ene
    -0.07
     Want
    -0.07
     Glam
    -0.07
    etch
    -0.07
    POSITIVE LOGITS
    hurst
    0.11
    AZY
    0.11
    Dlg
    0.11
    /logging
    0.10
     vis
    0.10
    spd
    0.10
    bdd
    0.10
    bstract
    0.10
     seg
    0.10
     immensely
    0.09
    Activations Density 0.009%

    No Known Activations