© 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. 3368
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    Negative Logits
     leap
    -0.06
     barg
    -0.06
    acious
    -0.06
     Chains
    -0.06
    faction
    -0.06
     chains
    -0.06
    ivas
    -0.06
    resses
    -0.06
     lang
    -0.06
    usher
    -0.06
    POSITIVE LOGITS
     thereof
    0.21
     ones
    0.13
    é¾
    0.13
     Mag
    0.12
    -than
    0.12
    Macro
    0.12
    -so
    0.11
    /dom
    0.11
    /extensions
    0.11
    soever
    0.11
    Activations Density 0.212%

    No Known Activations