© 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. 62617
    Prev
    Next
    INDEX
    Explanations

    trade system arrangements

    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
    粮油
    -0.09
    æ¶Įçİ°åĩº
    -0.09
    å¸IJ
    -0.09
    æĮĩæݧ
    -0.09
    åĴ«
    -0.08
    æŀľ
    -0.08
    注éĶĢ
    -0.08
    æĮijåīĶ
    -0.08
    rians
    -0.08
    ç´łè´¨æķĻèĤ²
    -0.08
    POSITIVE LOGITS
    å®īæİĴ
    0.13
     arrangements
    0.11
    erus
    0.10
     arrangement
    0.10
    åIJĪä½ľåħ³ç³»
    0.10
    æIJŃ
    0.09
    å±ĢéĿ¢
    0.09
     зай
    0.09
    æł¼å±Ģ
    0.09
    lake
    0.09
    Activations Density 0.085%

    No Known Activations