© 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. 22296
    Prev
    Next
    INDEX
    Explanations

    sounds, calls, singing, horns

    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
    é©®
    -0.09
    æĶ¾æīĭ
    -0.09
    åıĭæĥħ
    -0.09
    ç®´
    -0.09
    SWG
    -0.08
    å°»
    -0.08
    å°Ĩè¿İæĿ¥
    -0.08
    ä»ĩ
    -0.08
    åįłåľ°
    -0.08
    æĦıå¿Ĺ
    -0.08
    POSITIVE LOGITS
    åĸĩåıŃ
    0.12
    åIJ¹
    0.11
     whistle
    0.10
    çĮ¿
    0.10
    åij¼
    0.10
     horns
    0.10
     blow
    0.09
    åıijè¾¾
    0.09
    æĤł
    0.09
    笼
    0.09
    Activations Density 0.029%

    No Known Activations