© 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. 117562
    Prev
    Next
    INDEX
    Explanations

    explain behaviour, him, claims, announcement, achievement, skin, it, me, situation

    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
     convinc
    -0.12
    ulle
    -0.11
     chop
    -0.11
     seamlessly
    -0.10
     Bris
    -0.10
     RI
    -0.10
     effectively
    -0.10
    afen
    -0.10
    -ass
    -0.09
     smoothly
    -0.09
    POSITIVE LOGITS
     enough
    0.10
     Kore
    0.09
     Antony
    0.08
     possibilities
    0.08
     turnout
    0.08
    arl
    0.08
    evin
    0.08
     prospect
    0.08
    arin
    0.08
     Ced
    0.08
    Activations Density 0.164%

    No Known Activations