© 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. 29421
    Prev
    Next
    INDEX
    Explanations

    Morgan Phillips

    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
     Buf
    -0.09
     cg
    -0.08
     fal
    -0.08
    _pres
    -0.07
    sys
    -0.07
     frivol
    -0.07
     giveaways
    -0.07
    eah
    -0.07
    avel
    -0.07
     adm
    -0.07
    POSITIVE LOGITS
     Stretch
    0.11
     lurking
    0.10
    amil
    0.10
     Benn
    0.10
    Thought
    0.09
    *))
    0.09
     âĢķ
    0.09
     Travel
    0.09
     Wahl
    0.09
     Lonely
    0.09
    Activations Density 0.001%

    No Known Activations