© 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. 50141
    Prev
    Next
    INDEX
    Explanations

    names followed by magazine or locations

    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
     antic
    -0.08
     presum
    -0.08
    ly
    -0.08
    ziel
    -0.07
     straightforward
    -0.07
     cra
    -0.07
    lope
    -0.07
    uelle
    -0.07
     tertiary
    -0.06
     dram
    -0.06
    POSITIVE LOGITS
    crc
    0.13
    yards
    0.12
    iations
    0.11
    à§įà¦
    0.10
    crate
    0.10
    еÑĤÑģÑı
    0.10
     Jah
    0.10
     Yard
    0.10
    arily
    0.10
    Liked
    0.10
    Activations Density 0.006%

    No Known Activations