© 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. 33356
    Prev
    Next
    INDEX
    Explanations

    quantum mechanics

    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
    éĻįèIJ½
    -0.11
    uga
    -0.09
    èī¯
    -0.09
    æ»ŀåIJİ
    -0.09
    magic
    -0.09
    çŃĴ
    -0.08
     MAGIC
    -0.08
     Fuse
    -0.08
    icl
    -0.08
    ç«ĸ
    -0.08
    POSITIVE LOGITS
    éĩıåŃIJ
    0.13
     quantum
    0.12
    åİŁåŃIJ
    0.09
     Quantum
    0.09
    æºĸ
    0.09
    å®ŀçī©
    0.09
     Boh
    0.09
    èĥ½éĩı
    0.08
    åķ¤éħĴ
    0.08
    atura
    0.08
    Activations Density 0.058%

    No Known Activations