© 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. 8142
    Prev
    Next
    INDEX
    Explanations

    and, or, but

    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
    ÑĥÑģ
    -0.10
    imei
    -0.10
     Recomm
    -0.10
     recal
    -0.10
    owa
    -0.10
     âŁ
    -0.10
    ixin
    -0.10
    -es
    -0.10
    chsel
    -0.09
     forfe
    -0.09
    POSITIVE LOGITS
     also
    0.16
    also
    0.16
     ALSO
    0.14
     responsible
    0.14
    ä¹Ł
    0.12
    Also
    0.11
     Responsible
    0.10
     Also
    0.10
     equivalent
    0.10
     notoriously
    0.09
    Activations Density 0.371%

    No Known Activations