© 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. 3660
    Prev
    Next
    INDEX
    Explanations

    those of whom are unfamiliar

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Fi
    -0.12
    pery
    -0.11
    izada
    -0.11
     ironically
    -0.11
    imo
    -0.11
    raud
    -0.11
     Serving
    -0.11
    tte
    -0.11
     INCLUDING
    -0.11
    /fr
    -0.10
    POSITIVE LOGITS
     unfamiliar
    0.18
     wondering
    0.18
     unaware
    0.17
     interested
    0.14
     concerned
    0.13
     unsure
    0.12
     unknown
    0.11
     worried
    0.11
     curious
    0.11
     unclear
    0.11
    Activations Density 0.039%

    No Known Activations