© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60761
    Prev
    Next
    INDEX
    Explanations

    autonomous and autonomy

    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
    Negative Logits
    åIJ¯èĴĻ
    -0.10
    åĨķ
    -0.10
    iner
    -0.10
    主æĦı
    -0.10
    èµĦ产éĩįç»Ħ
    -0.09
    gs
    -0.09
    è¦ģç´§
    -0.09
    rlen
    -0.09
    è¨ĢãģĪãģ°
    -0.09
    ühr
    -0.09
    POSITIVE LOGITS
    èĩªä¸»
    0.11
    èĩªæ²»
    0.10
     autonom
    0.10
    ched
    0.09
     autonomy
    0.09
    RIES
    0.09
     fend
    0.09
     каÑĩ
    0.08
     autonomous
    0.08
    aris
    0.08
    Activations Density 0.022%

    No Known Activations