© 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. 41640
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or variables ($k, n, q, f, \forall$)

    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
     whatsoever
    -0.07
    å°±ç®ĹäºĨ
    -0.06
    eda
    -0.06
    ÙĪاÙĨ
    -0.06
    Ñĭ
    -0.06
    æİ·
    -0.06
    çģ«çĥŃçļĦ
    -0.06
    çŁŃç¯ĩå°ı说
    -0.06
    åĽºçĦ¶
    -0.06
    yc
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.08
    æĥĬå¿ĥ
    0.08
     dim
    0.08
    俱ä¹IJéĥ¨
    0.07
    hô
    0.07
    nok
    0.07
    dim
    0.07
    身临åħ¶å¢ĥ
    0.07
     ës
    0.07
    entena
    0.07
    Activations Density 0.008%

    No Known Activations