© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38714
    Prev
    Next
    INDEX
    Explanations

    attempt murder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    解åİĭ
    -0.08
     ìľµ
    -0.07
    apult
    -0.07
    æĤ¦
    -0.07
    é²²
    -0.07
    ẹp
    -0.06
    çݺ
    -0.06
    èŀįåIJĪ
    -0.06
    einander
    -0.06
    èŀį
    -0.06
    POSITIVE LOGITS
     homicide
    0.09
    åĪijæ³ķ
    0.09
    çĬ¯çļĦ
    0.08
    oriously
    0.08
     abortion
    0.07
    åı¯ä»¥åĪĨ为
    0.07
    åı¯åĪĨ为
    0.07
    æĿĢ人
    0.07
    çĬ¯
    0.07
    å±ķè§Īä¼ļ
    0.07
    Activations Density 0.002%

    No Known Activations