© 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. 56041
    Prev
    Next
    INDEX
    Explanations

    rules following the

    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
    omis
    -0.07
    å°½
    -0.06
    lander
    -0.06
     impres
    -0.06
    ä¸įçĿĢ
    -0.06
    è°ģ家
    -0.06
    游åŃIJ
    -0.06
    gard
    -0.06
    à¸ŀิมà¸ŀà¹Į
    -0.06
     Recovery
    -0.06
    POSITIVE LOGITS
    ueue
    0.10
    çĹº
    0.08
    uil
    0.08
    è§Ħå¾ĭ
    0.08
    è¦ıå¾ĭ
    0.08
    éĢ»
    0.08
    raphics
    0.08
    宾
    0.07
    空å¿ĥ
    0.07
    Denied
    0.07
    Activations Density 0.008%

    No Known Activations