© 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. 87842
    Prev
    Next
    INDEX
    Explanations

    vocaloid, vocational, vocals, voracious

    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
     Rhodes
    -0.11
     Coff
    -0.11
    /fast
    -0.10
    iano
    -0.10
     Birch
    -0.10
    astle
    -0.10
     Pact
    -0.09
     mosaic
    -0.09
     Bolt
    -0.09
     deducted
    -0.09
    POSITIVE LOGITS
     uncont
    0.10
     hed
    0.10
    aira
    0.09
     utter
    0.09
    zan
    0.09
    aal
    0.08
     exh
    0.08
    ukan
    0.08
    IPC
    0.08
     proph
    0.08
    Activations Density 0.005%

    No Known Activations