© 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. 8462
    Prev
    Next
    INDEX
    Explanations

    blindness and enlightenment

    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
    çĹķ
    -0.10
    åĿIJä¸ĭ
    -0.10
    ä¼ģ
    -0.09
    Trace
    -0.09
    æī¯
    -0.09
    éħĿéħ¿
    -0.09
    亲è¿ij
    -0.08
    ç´§å¼ł
    -0.08
    çļĦ家åºŃ
    -0.08
    å¤ĩ
    -0.08
    POSITIVE LOGITS
    çĽ²
    0.15
    æĹłçŁ¥
    0.14
     blind
    0.14
    blind
    0.13
     blindness
    0.12
    è§Ĩéĩİ
    0.12
    -blind
    0.12
    çĽ²çĽ®
    0.12
    çľ¼çĿĽ
    0.12
    çľ¼çķĮ
    0.12
    Activations Density 0.073%

    No Known Activations