© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7539
    Prev
    Next
    INDEX
    Explanations

    screen, intake, hook, penetration, Fly, Plug, Filter

    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
    èģĮå·¥
    -0.10
    è°§
    -0.09
    弥漫
    -0.09
    çĽijçĭ±
    -0.09
    èħ´
    -0.09
    åĪ°è¾¾
    -0.09
    çľĭä¸įåĪ°
    -0.08
    平淡
    -0.08
    ULT
    -0.08
    åįģéĩĮ
    -0.08
    POSITIVE LOGITS
    éĻĦ件
    0.09
    èĮ¨
    0.09
    åıijæĺİä¸ĵåĪ©
    0.09
    éĶĭ
    0.09
    enic
    0.09
    èĪª
    0.09
     Claus
    0.08
    åħīçݯ
    0.08
    çĥŃ线
    0.08
    èĪªçº¿
    0.08
    Activations Density 0.124%

    No Known Activations