© 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. 36312
    Prev
    Next
    INDEX
    Explanations

    fiber arts and materials

    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
    佩æĪ´
    -0.09
    åIJİæİĴ
    -0.09
    pest
    -0.09
    åĤij
    -0.09
    æīĭå¥Ĺ
    -0.09
    WithPath
    -0.09
    åIJ¬åıĸ
    -0.08
    åģľçķĻåľ¨
    -0.08
    æ±īåł¡
    -0.08
    çħ
    -0.08
    POSITIVE LOGITS
    æĿIJæĸĻ
    0.13
    æĸ°æĿIJæĸĻ
    0.12
    æĿIJ
    0.12
     materials
    0.11
    orado
    0.11
    materials
    0.10
    æĸĻ
    0.10
    ç´łæĿIJ
    0.10
    åı¯çĶ¨äºİ
    0.10
    _material
    0.10
    Activations Density 0.068%

    No Known Activations