© 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. 48772
    Prev
    Next
    INDEX
    Explanations

    success or positive 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
    çķĻä¸ĭäºĨ
    -0.10
     intercept
    -0.09
    æŃª
    -0.09
    elan
    -0.09
    _GC
    -0.08
    é«ĺ峰论åĿĽ
    -0.08
    illery
    -0.08
    bai
    -0.08
    ảo
    -0.08
    enis
    -0.08
    POSITIVE LOGITS
     success
    0.14
    äºĭä¸ļåıijå±ķ
    0.13
    å´Ľèµ·
    0.12
    æĪIJè´¥
    0.12
    åģ¥åº·åıijå±ķ
    0.12
     réuss
    0.11
    æĪIJåĬŁ
    0.11
     éxito
    0.11
    äºĭä¸ļ
    0.11
    涨
    0.11
    Activations Density 0.050%

    No Known Activations