© 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. 113432
    Prev
    Next
    INDEX
    Explanations

    leaked

    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
     vag
    -0.10
     Ire
    -0.09
    Flush
    -0.08
     rec
    -0.08
    irs
    -0.08
    Channels
    -0.08
     rupt
    -0.08
    eut
    -0.08
    lé
    -0.08
    FI
    -0.08
    POSITIVE LOGITS
     its
    0.14
     contents
    0.13
     forth
    0.13
     onto
    0.13
     information
    0.13
     bits
    0.12
    contents
    0.11
    information
    0.11
     electrons
    0.11
    ifen
    0.11
    Activations Density 0.069%

    No Known Activations