© 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. 16670
    Prev
    Next
    INDEX
    Explanations

    With (followed by 'the' or 'all' or 'just')

    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
    enton
    -0.11
    rag
    -0.11
     Cunning
    -0.10
    bon
    -0.10
     Rac
    -0.10
     bon
    -0.10
     div
    -0.10
    -reply
    -0.10
     tim
    -0.10
    목
    -0.09
    POSITIVE LOGITS
     subclass
    0.09
     McGu
    0.08
     forwards
    0.08
    以ä¸Ĭ
    0.08
     BU
    0.08
     Kl
    0.08
     debunk
    0.08
    ASI
    0.08
     precautions
    0.08
     tips
    0.08
    Activations Density 0.001%

    No Known Activations