© 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. 89388
    Prev
    Next
    INDEX
    Explanations

    Zhao, Alberto, Chile, paras

    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
    ience
    -0.08
     synerg
    -0.08
     brute
    -0.07
    iente
    -0.07
    verts
    -0.07
    reas
    -0.07
     Midnight
    -0.07
    ly
    -0.07
     forth
    -0.07
     rare
    -0.06
    POSITIVE LOGITS
     IReadOnly
    0.12
    RIX
    0.11
     Roths
    0.11
    etro
    0.11
    aphore
    0.11
    rix
    0.11
    anon
    0.11
    vard
    0.10
    .uuid
    0.10
    eted
    0.10
    Activations Density 0.010%

    No Known Activations