© 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. 3406
    Prev
    Next
    INDEX
    Explanations

    young and old

    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
    Negative Logits
     children
    -0.13
     child
    -0.11
    loom
    -0.10
    CHILD
    -0.10
    children
    -0.10
     chim
    -0.09
    child
    -0.09
     Child
    -0.09
     aggreg
    -0.09
     //=
    -0.09
    POSITIVE LOGITS
    swick
    0.09
    olders
    0.09
    brig
    0.09
    zac
    0.09
     vieux
    0.09
    rone
    0.09
     tatto
    0.09
     Finger
    0.09
    mouseup
    0.09
     invaders
    0.08
    Activations Density 0.071%

    No Known Activations