© 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. 14949
    Prev
    Next
    INDEX
    Explanations

    North with place names

    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
    ties
    -0.10
    ities
    -0.10
    ern
    -0.08
     dissent
    -0.08
     Valent
    -0.08
     disse
    -0.08
    boom
    -0.08
     Dove
    -0.08
    ablish
    -0.08
    parity
    -0.08
    POSITIVE LOGITS
    ampton
    0.15
     Carolina
    0.13
    umberland
    0.12
     America
    0.12
    volt
    0.11
    rup
    0.11
    ridge
    0.11
    America
    0.10
    WEST
    0.10
    cen
    0.10
    Activations Density 0.051%

    No Known Activations