© 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. 7400
    Prev
    Next
    INDEX
    Explanations

    dimensions or frame

    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
     {}\
    -0.08
    (_)
    -0.08
    .ua
    -0.08
     (=
    -0.08
     functional
    -0.07
    {}]
    -0.07
    yna
    -0.07
     (_)
    -0.07
    preced
    -0.07
    {}\
    -0.07
    POSITIVE LOGITS
     dimensions
    0.15
     Dimensions
    0.15
    dimensions
    0.14
    Dimensions
    0.14
    :
    0.14
     lx
    0.13
     [("
    0.12
    uste
    0.11
     stats
    0.11
     parameters
    0.11
    Activations Density 1.663%

    No Known Activations