© 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. 20319
    Prev
    Next
    INDEX
    Explanations

    is showing

    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
    绿水
    -0.10
    nds
    -0.10
    çī§
    -0.10
    åħĭ
    -0.10
    RTC
    -0.09
    è¿Ļç§įäºĭæĥħ
    -0.09
    æŀŀ
    -0.09
    èĢķ
    -0.09
    è¿Ļ家
    -0.09
     Grimm
    -0.08
    POSITIVE LOGITS
    æī¿
    0.10
    achte
    0.09
    éģĦ
    0.09
     rebound
    0.08
    anian
    0.08
     pity
    0.08
     Burst
    0.08
    !("{}",
    0.08
    åł¡
    0.08
     lã
    0.08
    Activations Density 0.309%

    No Known Activations