© 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. 8901
    Prev
    Next
    INDEX
    Explanations

    cars making noise

    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
    å¸®ä½ł
    -0.08
    èµı
    -0.08
    virt
    -0.08
    å¾ħ
    -0.08
    SHARE
    -0.08
     Nancy
    -0.08
    ạm
    -0.08
    .nc
    -0.08
     Ecc
    -0.08
    lec
    -0.08
    POSITIVE LOGITS
     roar
    0.13
    åĴĨ
    0.13
    æĮŁ
    0.10
    åļİ
    0.10
    åIJ¼
    0.09
    åıijåĩº
    0.09
     roaring
    0.09
    _VOICE
    0.09
    IJèĹı
    0.09
     noises
    0.09
    Activations Density 0.116%

    No Known Activations