© 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. 31440
    Prev
    Next
    INDEX
    Explanations

    interacting or dealing

    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
    tic
    -0.11
    RIC
    -0.11
    ulu
    -0.10
    ula
    -0.10
    inja
    -0.09
    ULA
    -0.09
    uling
    -0.09
    Matching
    -0.09
     gig
    -0.09
    ardy
    -0.08
    POSITIVE LOGITS
     interacting
    0.19
     dealing
    0.17
     unknow
    0.16
     interact
    0.15
     contacting
    0.15
     interacts
    0.14
     unwitting
    0.14
     dealings
    0.14
     interf
    0.14
     talking
    0.12
    Activations Density 0.187%

    No Known Activations