© 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. 33930
    Prev
    Next
    INDEX
    Explanations

    elephant room

    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
     isot
    -0.11
     praise
    -0.09
     atleast
    -0.09
    .xxx
    -0.09
    /Admin
    -0.09
    kaar
    -0.09
    ye
    -0.09
     decad
    -0.09
     slack
    -0.08
     turnover
    -0.08
    POSITIVE LOGITS
     elephant
    0.18
     Elephant
    0.15
     gor
    0.13
     room
    0.13
    .room
    0.13
     Room
    0.12
     glaring
    0.12
    Room
    0.11
    (room
    0.11
     ROOM
    0.11
    Activations Density 0.012%

    No Known Activations