© 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. 5459
    Prev
    Next
    INDEX
    Explanations

    bridges and related structures

    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
    inea
    -0.12
    tn
    -0.11
    amer
    -0.10
    ete
    -0.10
    eten
    -0.10
    neau
    -0.10
    uter
    -0.09
     Whip
    -0.09
     cliff
    -0.09
    cka
    -0.09
    POSITIVE LOGITS
     deck
    0.12
     undef
    0.12
    head
    0.12
     Deck
    0.10
     Hass
    0.10
     over
    0.10
     toll
    0.10
     bridge
    0.10
     spanning
    0.10
    urally
    0.10
    Activations Density 0.030%

    No Known Activations