© 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. 113452
    Prev
    Next
    INDEX
    Explanations

    displaying various types of content

    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
    erne
    -0.10
     Bark
    -0.10
    (.)
    -0.09
    èĪ
    -0.09
    onium
    -0.09
    Karen
    -0.08
    aramel
    -0.08
    /tutorial
    -0.08
    isp
    -0.08
    iken
    -0.08
    POSITIVE LOGITS
    -posts
    0.11
     display
    0.10
     displayed
    0.10
    HomeAsUpEnabled
    0.10
    elon
    0.10
    å±ķ
    0.10
    reative
    0.10
    alta
    0.10
     Hyde
    0.10
    -display
    0.09
    Activations Density 0.055%

    No Known Activations