© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19327
    Prev
    Next
    INDEX
    Explanations

    I like it too

    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
    èĬ
    -0.09
    éĶŃ
    -0.08
    ulty
    -0.08
    çĽ¥
    -0.08
     effectively
    -0.08
    ä¹ĭå¤ľ
    -0.08
    ç»ĻäºĪ
    -0.08
    åħ¨åİ¿
    -0.08
    iture
    -0.08
    èĵį
    -0.08
    POSITIVE LOGITS
    壤
    0.10
    带头
    0.09
     ayrıl
    0.09
    iej
    0.09
     enough
    0.08
    質
    0.08
    æ»ĭåij³
    0.08
    omens
    0.08
    irit
    0.08
    ãģĦãģı
    0.08
    Activations Density 0.030%

    No Known Activations