© 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. 4939
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
     exchanged
    -0.10
     Fur
    -0.10
     Lub
    -0.09
    essa
    -0.09
     interpersonal
    -0.09
     Kenn
    -0.09
     paired
    -0.09
     Hib
    -0.09
    fur
    -0.09
    enger
    -0.09
    POSITIVE LOGITS
     between
    0.39
    between
    0.33
     Between
    0.32
     BETWEEN
    0.28
    Between
    0.27
     zwischen
    0.23
    -between
    0.22
    /connection
    0.22
     connection
    0.21
     link
    0.21
    Activations Density 0.679%

    No Known Activations