© 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. 9888
    Prev
    Next
    INDEX
    Explanations

    specific connection or factor

    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
    ople
    -0.10
    åıī
    -0.09
    彦
    -0.09
    ë²Į
    -0.09
    ISO
    -0.09
    .Generated
    -0.09
    æľīåIJįçļĦ
    -0.09
    çĴľ
    -0.09
     Metro
    -0.08
    çģ«çĥ§
    -0.08
    POSITIVE LOGITS
    åįķä¸Ģ
    0.19
    åIJĮä¸Ģ个
    0.15
    ä¸Ģ家
    0.13
    æŁIJä¸Ģ
    0.12
    ä¸Ģ个èģĮä¸ļ
    0.12
    ä¸Ģ件äºĭæĥħ
    0.12
    åľ¨åIJĮä¸Ģ
    0.11
    ä¸Ģå¤Ħ
    0.11
    ä»»ä½ķä¸Ģ个
    0.11
    ä¸Ģ件äºĭ
    0.11
    Activations Density 0.203%

    No Known Activations