© 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. 31057
    Prev
    Next
    INDEX
    Explanations

    places starting with 'M' or 'L'

    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
    çļĦç¬ij容
    -0.10
    èħIJ
    -0.10
    åĨħéĻĨ
    -0.10
    é£İ鼨
    -0.10
    ç¬ij容
    -0.09
    éªĦåĤ²
    -0.09
    born
    -0.09
    çĸı
    -0.08
    ä¾ĽåºĶ
    -0.08
    é©¿
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.10
    iÄį
    0.10
    åı¯è§Ĥ
    0.09
    æīĢåľ¨
    0.09
    ä¸Ģ天
    0.09
    象
    0.09
     benches
    0.09
    çĿ¦
    0.08
    â¿
    0.08
    å°ĸ
    0.08
    Activations Density 0.117%

    No Known Activations