© 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. 5537
    Prev
    Next
    INDEX
    Explanations

    hanging or attached

    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
     heaps
    -0.10
     heap
    -0.10
     piles
    -0.09
     Heap
    -0.09
     lif
    -0.09
     Coff
    -0.08
     piled
    -0.08
     coffin
    -0.08
     dropping
    -0.08
     bom
    -0.08
    POSITIVE LOGITS
    Hang
    0.12
     Vie
    0.12
     hung
    0.11
     prepar
    0.11
    hook
    0.11
     hook
    0.10
     hang
    0.10
    prar
    0.10
     hanging
    0.10
     unavailable
    0.10
    Activations Density 0.010%

    No Known Activations