© 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. 87668
    Prev
    Next
    INDEX
    Explanations

    key followed by `a` or `_`

    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
    acf
    -0.11
    arih
    -0.11
     ninete
    -0.10
    lfw
    -0.10
    eah
    -0.10
    asu
    -0.10
    aju
    -0.10
     VII
    -0.10
    odi
    -0.09
     eighteen
    -0.09
    POSITIVE LOGITS
    1
    0.12
    2
    0.11
     third
    0.10
    3
    0.09
     THIRD
    0.09
     Rossi
    0.09
    Third
    0.08
     bons
    0.08
    esp
    0.08
    AXB
    0.08
    Activations Density 0.471%

    No Known Activations