© 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. 16627
    Prev
    Next
    INDEX
    Explanations

    iggy, igg, occ, idd, gl suffixes

    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
     Spit
    -0.10
    ed
    -0.10
    rans
    -0.09
     closely
    -0.09
    eron
    -0.09
    asta
    -0.09
     clipboard
    -0.09
    chn
    -0.08
    ré
    -0.08
    bers
    -0.08
    POSITIVE LOGITS
    LES
    0.12
    les
    0.11
    urat
    0.11
     #:
    0.11
    ypad
    0.10
    lesh
    0.10
    ernet
    0.10
    ymoon
    0.09
     Backbone
    0.09
    ilik
    0.09
    Activations Density 0.006%

    No Known Activations