© 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. 115294
    Prev
    Next
    INDEX
    Explanations

    culturally, cultivated, cultivation, culture

    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
    endo
    -0.08
    ardy
    -0.08
    /rules
    -0.08
     Energ
    -0.08
     Bust
    -0.07
    endor
    -0.07
    ignon
    -0.07
    Headers
    -0.07
     backing
    -0.07
    isper
    -0.07
    POSITIVE LOGITS
    inel
    0.12
    dsl
    0.11
    ivals
    0.11
    angen
    0.11
    mpp
    0.11
    eil
    0.10
    emi
    0.10
     Ged
    0.10
     corporation
    0.10
     mav
    0.10
    Activations Density 0.001%

    No Known Activations