© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16770
    Prev
    Next
    INDEX
    Explanations

    murder and killing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æĹĹ
    -0.08
    iede
    -0.06
    æĬ½
    -0.06
    æĹ
    -0.06
    Flags
    -0.06
     flags
    -0.06
    wo
    -0.06
    orage
    -0.06
    _FLAG
    -0.06
    æĹĹå¸ľ
    -0.06
    POSITIVE LOGITS
    åIJĥèĤī
    0.06
    rous
    0.06
    ÑĤÑĬ
    0.06
     prolific
    0.06
    èħ»
    0.06
    æĭīåħĭ
    0.06
    æ
    0.06
     facult
    0.05
    æĪĸå¤ļæĪĸå°ij
    0.05
     forgiving
    0.05
    Activations Density 0.028%

    No Known Activations