© 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. 25260
    Prev
    Next
    INDEX
    Explanations

    yo or y

    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
     rel
    -0.15
    orde
    -0.09
    tle
    -0.09
    kus
    -0.09
     Griffin
    -0.08
     Bre
    -0.08
     talks
    -0.08
    chten
    -0.08
    esis
    -0.08
    umba
    -0.08
    POSITIVE LOGITS
    inki
    0.11
    ingu
    0.10
    Yo
    0.10
     cyc
    0.10
    hei
    0.10
     OSI
    0.09
    oyo
    0.09
     hitch
    0.09
     OTA
    0.09
     Zur
    0.09
    Activations Density 0.031%

    No Known Activations