© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    SQL, code snippets, headers, numbers

    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
     Alone
    -0.10
    695
    -0.09
     relax
    -0.09
     conclude
    -0.09
     ever
    -0.09
    asters
    -0.08
     Gib
    -0.08
     rhe
    -0.08
    596
    -0.08
     slips
    -0.08
    POSITIVE LOGITS
    ä½ķ
    0.10
     wanna
    0.10
     specifics
    0.10
     mattered
    0.09
    fare
    0.09
    ume
    0.09
     unquestion
    0.09
    anything
    0.09
     how
    0.09
    SEL
    0.09
    Activations Density 0.004%

    No Known Activations