© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 30094
    Prev
    Next
    INDEX
    Explanations

    service, policy, notice, journal, analysis, williams

    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
     Coff
    -0.09
     peeled
    -0.09
    ippi
    -0.09
    éľ
    -0.08
    viewer
    -0.08
     commons
    -0.08
    EB
    -0.08
     ko
    -0.08
     sims
    -0.08
    LAN
    -0.08
    POSITIVE LOGITS
     Eig
    0.10
    stin
    0.10
    OAD
    0.09
     Publications
    0.09
    rong
    0.09
    uin
    0.09
     âĢķ
    0.09
     colour
    0.09
     Bread
    0.09
     basically
    0.09
    Activations Density 0.001%

    No Known Activations