© 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. 18731
    Prev
    Next
    INDEX
    Explanations

    vainly tried

    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
    /exp
    -0.11
     Wein
    -0.11
    ime
    -0.11
     perv
    -0.11
    iou
    -0.11
     Directed
    -0.11
     innocent
    -0.10
     Mein
    -0.10
     diminishing
    -0.10
    oder
    -0.10
    POSITIVE LOGITS
     you
    0.10
     myself
    0.10
     vaguely
    0.09
    angler
    0.09
     been
    0.08
     faint
    0.08
    want
    0.08
    -ser
    0.08
     eagerly
    0.07
    fully
    0.07
    Activations Density 0.002%

    No Known Activations