© 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. 117078
    Prev
    Next
    INDEX
    Explanations

    untangled or tangled knot

    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
     governors
    -0.12
     Governors
    -0.11
    Govern
    -0.11
     mojo
    -0.09
     spanking
    -0.09
    nal
    -0.09
    unda
    -0.09
     Governor
    -0.09
    avage
    -0.09
    idine
    -0.09
    POSITIVE LOGITS
     knots
    0.20
     tangled
    0.20
     knot
    0.18
     Knot
    0.18
     wires
    0.16
     cords
    0.16
     vines
    0.16
     ske
    0.15
     ropes
    0.14
     intertwined
    0.14
    Activations Density 0.046%

    No Known Activations