© 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. 14251
    Prev
    Next
    INDEX
    Explanations

    information or clues to find answers

    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
    ignon
    -0.12
     Lob
    -0.11
    KB
    -0.11
     claimed
    -0.11
    onde
    -0.10
     Palm
    -0.10
    ulla
    -0.10
    @dynamic
    -0.10
     SUMMARY
    -0.10
    NU
    -0.10
    POSITIVE LOGITS
     clues
    0.29
     clue
    0.27
     hint
    0.17
     hints
    0.16
     leads
    0.14
     useful
    0.14
     helpful
    0.13
     usable
    0.12
     tantal
    0.12
    hint
    0.12
    Activations Density 0.208%

    No Known Activations