© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20808
    Prev
    Next
    INDEX
    Explanations

    salad or shoulder

    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
    åĸ·æ¶Ĥ
    -0.10
    沫
    -0.10
     обÑıз
    -0.09
    åŃĶåŃIJ
    -0.09
    å·¡
    -0.09
    èĥĢ
    -0.09
    çĨ¬
    -0.09
    礼
    -0.09
    ipel
    -0.08
    .ids
    -0.08
    POSITIVE LOGITS
     <![
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    aldi
    0.09
    Cycle
    0.08
    æŃ¢
    0.08
     Canter
    0.08
    anol
    0.08
    ãģ£ãģ±
    0.08
    大éĻĨ
    0.08
    ycles
    0.08
    Activations Density 0.051%

    No Known Activations