© 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. 6472
    Prev
    Next
    INDEX
    Explanations

    Oxford University

    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
    bih
    -0.09
    iffe
    -0.08
     Seattle
    -0.08
    ipes
    -0.08
    Seattle
    -0.08
    rip
    -0.08
    ensions
    -0.08
    ARAM
    -0.08
    iper
    -0.08
    /release
    -0.07
    POSITIVE LOGITS
    shire
    0.18
     Circus
    0.14
    compass
    0.12
    ÑģÑı
    0.10
     CCC
    0.10
    alic
    0.10
     COMP
    0.10
    toc
    0.10
     commas
    0.10
     circus
    0.10
    Activations Density 0.034%

    No Known Activations