© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7936
    Prev
    Next
    INDEX
    Explanations

    effects, actions, options, changes

    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
    Ľå»º
    -0.08
    aben
    -0.08
     Jacqu
    -0.08
     reb
    -0.07
    irie
    -0.07
    iset
    -0.07
    ighton
    -0.07
    anken
    -0.07
     ISSUE
    -0.07
    âĢIJ
    -0.07
    POSITIVE LOGITS
    obar
    0.10
    olie
    0.10
     aka
    0.10
    oren
    0.10
    dob
    0.10
    witter
    0.10
     berk
    0.09
    /-
    0.09
    yas
    0.09
    ovi
    0.09
    Activations Density 1.874%

    No Known Activations