© 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. 46351
    Prev
    Next
    INDEX
    Explanations

    disease, study, controversy, law, discussion

    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
    ame
    -0.11
    iev
    -0.08
    iete
    -0.08
    quo
    -0.08
    noch
    -0.08
     Lindsay
    -0.08
     mend
    -0.08
     winding
    -0.08
    Chuck
    -0.07
     irreversible
    -0.07
    POSITIVE LOGITS
    们
    0.20
    sWith
    0.20
    (s
    0.19
    [s
    0.19
    swith
    0.19
    ات
    0.17
    ëĵ¤
    0.16
    sto
    0.14
    sthrough
    0.14
    ss
    0.14
    Activations Density 1.040%

    No Known Activations