© 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. 63141
    Prev
    Next
    INDEX
    Explanations

    death, injury, or legal proceedings

    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
    åİ»ä¸ĸ
    -0.16
     deceased
    -0.15
    æŃ»äº¡
    -0.15
    æŃ»èĢħ
    -0.14
    dead
    -0.14
    æŃ»äºĨ
    -0.14
    æŃ»åİ»
    -0.13
    æŃ»åIJİ
    -0.13
     dead
    -0.13
     death
    -0.13
    POSITIVE LOGITS
    æijĬ
    0.10
    ulet
    0.10
    åIJ¬å®Į
    0.09
    ä¸Ģéģį
    0.09
    uc
    0.09
    chr
    0.09
    æ´
    0.08
    åıĹéĤĢ
    0.08
    .poster
    0.08
    æĭ¥
    0.08
    Activations Density 0.035%

    No Known Activations