© 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. 37412
    Prev
    Next
    INDEX
    Explanations

    glass and its manufacturing

    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
    å°ģéĿ¢
    -0.09
    ä¸Ģ棵
    -0.09
    æłħ
    -0.09
    é²ľ
    -0.09
    ngth
    -0.08
    åı°è´¦
    -0.08
    第ä¸ĢæŶéĹ´
    -0.08
    éĻIJ
    -0.08
    Detach
    -0.08
    .oc
    -0.08
    POSITIVE LOGITS
    çİ»çĴĥ
    0.14
    Glass
    0.14
     Glass
    0.13
     glass
    0.13
    glass
    0.13
    glas
    0.12
    壶
    0.10
     Glas
    0.10
    agma
    0.09
    çİ»
    0.09
    Activations Density 0.091%

    No Known Activations