© 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. 46301
    Prev
    Next
    INDEX
    Explanations

    commands and invitations

    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
    utos
    -0.12
     Strauss
    -0.11
     ancest
    -0.11
    osemite
    -0.11
    ynn
    -0.11
    OLLOW
    -0.11
    asher
    -0.11
    arro
    -0.11
    -0.11
    cks
    -0.11
    POSITIVE LOGITS
     Your
    0.13
     hassle
    0.10
    ting
    0.09
     unleash
    0.09
     Hass
    0.08
     convenient
    0.08
     unle
    0.08
    endor
    0.08
     MOD
    0.08
     your
    0.08
    Activations Density 0.011%

    No Known Activations