© 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. 25758
    Prev
    Next
    INDEX
    Explanations

    intertwine or collide

    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
    apore
    -0.11
     collectively
    -0.11
     slack
    -0.11
     Ludwig
    -0.11
     autonomy
    -0.10
     Undo
    -0.10
    -w
    -0.10
     averaging
    -0.10
    tim
    -0.10
    afe
    -0.10
    POSITIVE LOGITS
     intertw
    0.18
     collide
    0.17
     seamlessly
    0.16
     intertwined
    0.15
     mingle
    0.15
     ming
    0.14
     collided
    0.14
     intersect
    0.14
     harmon
    0.14
     blend
    0.13
    Activations Density 0.024%

    No Known Activations