© 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. 52733
    Prev
    Next
    INDEX
    Explanations

    seems obvious, that, wrong, like, to

    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
    æŀ¶
    -0.10
    é¡¿
    -0.09
     envelop
    -0.08
    aster
    -0.08
    åį³åı¯
    -0.08
     gra
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    apore
    -0.08
    æ¥Ŀ
    -0.08
    æŃ£å¸¸ä½¿çĶ¨
    -0.08
    POSITIVE LOGITS
    æĪijè§īå¾Ĺ
    0.19
    åľ¨æĪijçľĭæĿ¥
    0.19
    æĪij认为
    0.19
    æĪij们认为
    0.14
    æĪijçľĭ
    0.12
    æĪij以为
    0.11
    otte
    0.10
    æĪijæĥ³
    0.10
    对æĪijæĿ¥è¯´
    0.10
    ãģłãģ¨æĢĿãģĨ
    0.10
    Activations Density 0.071%

    No Known Activations