© 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. 18377
    Prev
    Next
    INDEX
    Explanations

    decaying wood and logs

    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
     Maj
    -0.09
    maj
    -0.08
     blinking
    -0.08
     rud
    -0.07
     lightly
    -0.07
    imen
    -0.07
    uby
    -0.07
     Giles
    -0.07
     Mayer
    -0.07
    iland
    -0.07
    POSITIVE LOGITS
     rotten
    0.22
     decay
    0.20
     rot
    0.19
    decay
    0.17
    rot
    0.17
     Rot
    0.15
     smelling
    0.15
     Decay
    0.15
     spoiled
    0.14
    (rot
    0.14
    Activations Density 0.083%

    No Known Activations