© 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. 15281
    Prev
    Next
    INDEX
    Explanations

    Sakawa, Sakamoto, Sakari

    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
    åĬ
    -0.09
    coh
    -0.09
     narrow
    -0.08
     collectively
    -0.08
    -inst
    -0.08
    deen
    -0.08
    igel
    -0.07
    stime
    -0.07
    azz
    -0.07
    ffi
    -0.07
    POSITIVE LOGITS
     Wass
    0.12
     mor
    0.10
    song
    0.10
    sure
    0.09
     swamp
    0.09
     imp
    0.09
    ัà¸ļ
    0.09
     Patricia
    0.09
    paces
    0.09
    expo
    0.09
    Activations Density 0.006%

    No Known Activations