© 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. 49223
    Prev
    Next
    INDEX
    Explanations

    power interruption

    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
    å¼Ģå°ģ
    -0.10
    åIJ¹
    -0.09
    åı¯è§Ĩ
    -0.09
    è¯
    -0.09
    æ¸ĹéĢı
    -0.08
    ollo
    -0.08
    èµ·åĪĿ
    -0.08
    æŃ©
    -0.08
     blindness
    -0.08
     nostalg
    -0.08
    POSITIVE LOGITS
    çįIJ
    0.10
     shutdown
    0.10
    æĴ¤
    0.09
    æĴ¤ç¦»
    0.09
    åħ³éĹŃ
    0.09
    æ¼±
    0.09
    å½ķ
    0.09
    .Fat
    0.08
    åħ³
    0.08
     Ston
    0.08
    Activations Density 0.101%

    No Known Activations