© 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. 2739
    Prev
    Next
    INDEX
    Explanations

    actions related to information and objects

    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
    ä»Ģä¹Īä¸ľè¥¿
    -0.10
     Boeh
    -0.09
    è°
    -0.09
    ä½łè§īå¾Ĺ
    -0.09
    æĪĸå¤ļ
    -0.09
    /by
    -0.09
    è¿Ļ件äºĭ
    -0.08
    ä»Ģä¹Īäºĭ
    -0.08
    sst
    -0.08
    ambi
    -0.08
    POSITIVE LOGITS
     sobie
    0.11
     Ñģебе
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    çľŁç©º
    0.09
    å¼ĢæĿ¥
    0.09
    ARSE
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    æĺ¯æĪijçļĦ
    0.08
    æİ°
    0.08
    é¤IJ
    0.08
    Activations Density 0.207%

    No Known Activations