© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33731
    Prev
    Next
    INDEX
    Explanations

    cognitive impairment and styles

    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
    igne
    -0.12
     Lau
    -0.12
    540
    -0.11
    ichi
    -0.10
     parch
    -0.10
    fleet
    -0.10
    alar
    -0.09
    enko
    -0.09
    loo
    -0.09
     restitution
    -0.09
    POSITIVE LOGITS
    dle
    0.09
    ed
    0.09
     conce
    0.09
     Hover
    0.08
    nets
    0.08
     consul
    0.08
     haze
    0.08
     Weekly
    0.08
    ep
    0.08
    /ne
    0.08
    Activations Density 0.011%

    No Known Activations