© 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. 8186
    Prev
    Next
    INDEX
    Explanations

    Black [.[_ , Star|Stone|Cond|Creek|Press|Ey]

    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
     doPost
    -0.10
    grunt
    -0.10
     unearth
    -0.09
     rational
    -0.09
    _blocking
    -0.09
     McKenzie
    -0.09
    TF
    -0.09
    æĮ
    -0.09
     fair
    -0.09
     grandparents
    -0.09
    POSITIVE LOGITS
    /black
    0.17
    .Black
    0.15
     Black
    0.15
    Black
    0.14
    listed
    0.12
     Ops
    0.11
     black
    0.11
     é»
    0.11
    black
    0.11
    BLACK
    0.10
    Activations Density 0.207%

    No Known Activations