© 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. 53409
    Prev
    Next
    INDEX
    Explanations

    makes or limits outcomes

    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
    eland
    -0.10
    abis
    -0.09
    åıijçĶŁåľ¨
    -0.09
    ignon
    -0.09
    è¿Ī
    -0.09
    glomer
    -0.08
    çīĮåŃIJ
    -0.08
    resse
    -0.08
     Greene
    -0.08
    ä»ĭ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.15
    è¿Ľä¸ĢæŃ¥
    0.11
    åĨįåĬłä¸Ĭ
    0.11
    è¿Ļä¸ĢçĤ¹
    0.11
     further
    0.10
    0
    0.10
    å¢ŀåĬłäºĨ
    0.09
    éĢ²ä¸ĢæŃ¥
    0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    åĬłæĮģ
    0.09
    Activations Density 0.127%

    No Known Activations