© 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. 51310
    Prev
    Next
    INDEX
    Explanations

    successful performance descriptors

    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
    çģĮ
    -0.11
    æĶ¾å®½
    -0.09
    大äºĭ
    -0.08
    é»ijå¤ľ
    -0.08
     Nut
    -0.08
    akk
    -0.08
     Farr
    -0.08
    人æ°Ķ
    -0.08
    _dl
    -0.08
     ferr
    -0.08
    POSITIVE LOGITS
    åĬłåħ¥äºĨ
    0.09
    нал
    0.09
    ç¿
    0.09
    Ñĩи
    0.09
    æĺŁç©º
    0.09
    .Serve
    0.09
    çĶŁäº§æĢ»
    0.09
    PY
    0.09
    ÑĤал
    0.09
    CLUD
    0.09
    Activations Density 0.033%

    No Known Activations