© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    why things happen

    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
    963
    -0.11
     autof
    -0.11
     Mob
    -0.11
    -msg
    -0.10
    OOT
    -0.10
     Roch
    -0.10
    illo
    -0.10
     camel
    -0.10
    ILLE
    -0.10
    isl
    -0.10
    POSITIVE LOGITS
     what
    0.18
    what
    0.13
     as
    0.13
     whatever
    0.11
     where
    0.10
     tão
    0.09
    thew
    0.09
    arget
    0.09
    ien
    0.08
     wherever
    0.08
    Activations Density 0.117%

    No Known Activations