© 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. 50691
    Prev
    Next
    INDEX
    Explanations

    thoughts and remembrance

    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
     thoughts
    -0.11
     Thoughts
    -0.09
     Hund
    -0.09
     seam
    -0.09
    think
    -0.08
    zem
    -0.08
     programm
    -0.08
     thinks
    -0.08
    æĢĿ
    -0.08
     THINK
    -0.08
    POSITIVE LOGITS
     him
    0.11
     reaches
    0.11
    obi
    0.11
    ini
    0.10
     reaching
    0.10
     missed
    0.10
     laughing
    0.10
    allo
    0.10
    adt
    0.10
     laugh
    0.10
    Activations Density 0.025%

    No Known Activations