© 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. 112572
    Prev
    Next
    INDEX
    Explanations

    introductions and India

    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
    oord
    -0.12
     scandals
    -0.12
     praises
    -0.12
     Interr
    -0.12
     legitim
    -0.12
     Curtis
    -0.11
     _$
    -0.11
    Pas
    -0.11
    vip
    -0.11
     juicy
    -0.11
    POSITIVE LOGITS
     indian
    0.11
     india
    0.10
     India
    0.10
     &
    0.10
     Indian
    0.10
    India
    0.09
     kindly
    0.09
     Ms
    0.09
    Indian
    0.09
     techno
    0.08
    Activations Density 3.334%

    No Known Activations