© 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. 111462
    Prev
    Next
    INDEX
    Explanations

    substantia portions of

    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
    umph
    -0.10
    lost
    -0.10
    into
    -0.10
     (?,
    -0.09
    Lost
    -0.09
    gre
    -0.09
     Lost
    -0.09
    awe
    -0.09
    CustomLabel
    -0.09
    064
    -0.09
    POSITIVE LOGITS
    ĥģ
    0.08
    alf
    0.08
     hÃłng
    0.08
    ocz
    0.08
     mixture
    0.08
    lesen
    0.08
    moid
    0.08
     ready
    0.08
     matters
    0.08
     trends
    0.08
    Activations Density 0.001%

    No Known Activations