© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37389
    Prev
    Next
    INDEX
    Explanations

    should not be

    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
    è´´å¿ĥ
    -0.10
    esti
    -0.09
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.09
    oust
    -0.09
    使ä¹ĭ
    -0.09
     Yad
    -0.09
     bell
    -0.08
     gast
    -0.08
     Dial
    -0.08
    æĺİæĺİ
    -0.08
    POSITIVE LOGITS
    åĭ¿
    0.12
    è§Ĩ为
    0.11
    å½ĵä½ľ
    0.10
    çľĭå¾ħ
    0.10
    è¶ģ
    0.10
    çIJĨ解
    0.09
    碧
    0.09
    çľĭæ³ķ
    0.09
    å½ĵæĪIJ
    0.09
    ä¾®
    0.09
    Activations Density 0.057%

    No Known Activations