© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35618
    Prev
    Next
    INDEX
    Explanations

    dining room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    ween
    -0.10
    ä¸įçIJĨ
    -0.10
    è¦ģçľĭ
    -0.09
    ť
    -0.09
    ä¸Ńæĸ°ç½ij
    -0.09
    ifications
    -0.09
    æ¾Į
    -0.09
    è¡ĮæĶ¿åĮº
    -0.09
    éĩįè¦ģåİŁåĽł
    -0.09
    便åĪ©
    -0.09
    POSITIVE LOGITS
    itian
    0.08
     Banc
    0.08
    eenth
    0.08
     Burnett
    0.08
    cloth
    0.08
     Giuliani
    0.08
    ausal
    0.08
    олÑĮз
    0.08
     Hancock
    0.08
    NCY
    0.07
    Activations Density 0.004%

    No Known Activations