© 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. 6646
    Prev
    Next
    INDEX
    Explanations

    yet, already, created, initialization, years ago

    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
    å·¥
    -0.09
    磫
    -0.08
     hack
    -0.08
    èµĺ
    -0.08
    çļĦæľĢåIJİä¸Ģ
    -0.08
    æī¿æĭħ
    -0.08
     exc
    -0.08
    ä¸Ģåı£æ°Ķ
    -0.08
     charset
    -0.07
     mate
    -0.07
    POSITIVE LOGITS
    éĤ£æŶåĢĻ
    0.14
    éĤ£æŶ
    0.13
    å½ĵæŶ
    0.13
    å°ļæľª
    0.12
    è¿ĺ没æľī
    0.12
    è¿ĺæľª
    0.12
    è¿ĺ没
    0.12
    æł¹æľ¬ä¸į
    0.11
    åľ¨æѤä¹ĭåīį
    0.11
    çķ¶æĻĤ
    0.11
    Activations Density 0.215%

    No Known Activations