© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114870
    Prev
    Next
    INDEX
    Explanations

    public and private

    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
    @stop
    -0.10
     Lowell
    -0.10
    ãĤ¹ãĥĪ
    -0.10
    sted
    -0.10
    apan
    -0.09
    (::
    -0.09
     STDOUT
    -0.09
    _NATIVE
    -0.09
     Laurent
    -0.09
    stad
    -0.09
    POSITIVE LOGITS
     private
    0.39
     privately
    0.34
     Private
    0.33
     PRIVATE
    0.32
    private
    0.32
    Private
    0.29
    -private
    0.28
    ç§ģ
    0.26
    PRIVATE
    0.26
    /private
    0.26
    Activations Density 0.271%

    No Known Activations