© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5873
    Prev
    Next
    INDEX
    Explanations

    hands and feet

    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
     hands
    -0.21
     Hands
    -0.19
    Hands
    -0.17
     handheld
    -0.17
     handmade
    -0.16
    hands
    -0.15
    æīĭ
    -0.13
     handbook
    -0.13
     Harness
    -0.13
    .hashCode
    -0.13
    POSITIVE LOGITS
    .RequestMapping
    0.09
    unner
    0.08
     Peek
    0.08
     forearm
    0.08
    lyn
    0.08
     Wilson
    0.08
     isot
    0.08
    peek
    0.08
     legislation
    0.08
    eria
    0.08
    Activations Density 0.156%

    No Known Activations