© 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. 33406
    Prev
    Next
    INDEX
    Explanations

    best practices

    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
     studios
    -0.08
     Sik
    -0.07
     drifting
    -0.07
     deeper
    -0.07
    _nt
    -0.07
     Nicht
    -0.07
    osl
    -0.07
     studio
    -0.07
     clashes
    -0.07
    apper
    -0.07
    POSITIVE LOGITS
     Impl
    0.12
     Woods
    0.11
    enis
    0.11
     IMO
    0.11
     shortcode
    0.10
     woods
    0.10
     vale
    0.10
     fullscreen
    0.10
     lem
    0.10
     explos
    0.10
    Activations Density 0.001%

    No Known Activations