© 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. 8337
    Prev
    Next
    INDEX
    Explanations

    throwing away or out

    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
     knees
    -0.10
     closure
    -0.09
    adin
    -0.09
     ref
    -0.09
     closures
    -0.09
     Casc
    -0.09
     knocks
    -0.08
     humor
    -0.08
    atto
    -0.08
     unarmed
    -0.08
    POSITIVE LOGITS
     away
    0.15
    Dub
    0.13
     Away
    0.12
     Dub
    0.12
     offending
    0.11
    Away
    0.10
     trash
    0.10
     dub
    0.10
    WL
    0.09
     out
    0.09
    Activations Density 0.045%

    No Known Activations