© 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. 34302
    Prev
    Next
    INDEX
    Explanations

    kill puppies

    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
    ãģĸãģ¾
    -0.08
    -tools
    -0.08
    epen
    -0.07
    pruch
    -0.07
    層
    -0.07
    ecil
    -0.07
    å°§
    -0.07
    Linear
    -0.07
    Wunused
    -0.07
    éĶ»
    -0.07
    POSITIVE LOGITS
    ÙĨاÙĤ
    0.06
    ç¼¥
    0.06
    è°ģçŁ¥éģĵ
    0.06
     Convention
    0.06
    pres
    0.06
    idel
    0.06
    çĹħ
    0.06
    immers
    0.06
    æį
    0.06
    åĩºäºĨ
    0.06
    Activations Density 0.002%

    No Known Activations