© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7789
    Prev
    Next
    INDEX
    Explanations

    state of denial or delusion

    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
    纪å§Ķ
    -0.09
    -minus
    -0.09
    éľĩæħij
    -0.09
     Nude
    -0.09
    ait
    -0.09
     Nunes
    -0.08
     Astroph
    -0.08
     Specs
    -0.08
    EDGE
    -0.08
    åIJĵå¾Ĺ
    -0.08
    POSITIVE LOGITS
    鸵
    0.16
    çİ°å®ŀ
    0.11
    ideal
    0.10
    èĶ½
    0.10
    çļĦç¾İ好
    0.10
    ç¾İ好çļĦ
    0.10
    ç¾İ好çĶŁæ´»
    0.10
    翳
    0.10
    çı¾å¯¦
    0.10
    çīĩéĿ¢
    0.09
    Activations Density 0.058%

    No Known Activations