© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34851
    Prev
    Next
    INDEX
    Explanations

    lost or valuable time

    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
    æĭĹ
    -0.11
    澡
    -0.10
    è¦ĨçĽĸçİĩ
    -0.10
    plate
    -0.09
    æĥ³æ³ķ
    -0.09
    èµ·ä¼ı
    -0.09
    rive
    -0.09
    åĪĨæķ°çº¿
    -0.09
    ãĥŀãĥ³
    -0.09
    tier
    -0.08
    POSITIVE LOGITS
    æŶéĹ´åĴĮ
    0.14
    æĭĸ延
    0.14
    èĢ½
    0.13
    æŶéĹ´
    0.13
     time
    0.13
    èĬĤçľģ
    0.13
    çļĦæŶéĹ´
    0.12
    æĻĤéĸĵ
    0.12
    å®Ŀè´µ
    0.12
     вÑĢемÑı
    0.11
    Activations Density 0.058%

    No Known Activations