© 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. 88999
    Prev
    Next
    INDEX
    Explanations

    COPYRIGHT, SSL, and source code licenses

    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
     sol
    -0.08
    ZY
    -0.08
    blo
    -0.08
     Sok
    -0.08
    ikan
    -0.07
    olen
    -0.07
    iero
    -0.07
     Solomon
    -0.07
     bo
    -0.07
    олÑĮ
    -0.07
    POSITIVE LOGITS
    inite
    0.11
    izu
    0.10
     Benedict
    0.10
     promot
    0.10
    icer
    0.10
     penn
    0.10
     SOM
    0.10
    inz
    0.10
    gv
    0.10
     Buck
    0.10
    Activations Density 0.934%

    No Known Activations