© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    awards and achievements

    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
    bek
    -0.08
    cliffe
    -0.08
    ifo
    -0.08
    agas
    -0.08
    (CharSequence
    -0.08
    ,module
    -0.08
    .codes
    -0.08
     Executors
    -0.07
    íĺ¸
    -0.07
     fors
    -0.07
    POSITIVE LOGITS
    âĦ¢
    0.16
    ©
    0.13
    âĢİ
    0.12
    /Gate
    0.12
     II
    0.11
    TM
    0.11
     Redux
    0.10
     III
    0.10
    ssp
    0.10
    ®
    0.10
    Activations Density 1.401%

    No Known Activations