© 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. 15653
    Prev
    Next
    INDEX
    Explanations

    subject of attention or desire

    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
     personalities
    -0.10
     excuse
    -0.09
    urre
    -0.09
    annot
    -0.08
     personality
    -0.08
     coll
    -0.08
     rank
    -0.07
     bodies
    -0.07
    ushi
    -0.07
     rationale
    -0.07
    POSITIVE LOGITS
     affection
    0.22
     attention
    0.20
     ire
    0.19
     Attention
    0.17
     admiration
    0.17
     attent
    0.16
     interest
    0.15
    attention
    0.15
     scrutiny
    0.15
    Attention
    0.15
    Activations Density 0.073%

    No Known Activations