© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17690
    Prev
    Next
    INDEX
    Explanations

    | (HT, PN, SN)

    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
    GM
    -0.06
     Dol
    -0.06
    åĪ©
    -0.06
    èĭ¹
    -0.06
    afa
    -0.06
     Force
    -0.06
     Nata
    -0.06
     Boss
    -0.06
    Ñĥй
    -0.06
     g
    -0.06
    POSITIVE LOGITS
    æĹłè®ºæĺ¯
    0.16
    ä¸į管æĺ¯
    0.16
    ä¸į论æĺ¯
    0.14
    å°¤åħ¶æĺ¯
    0.13
    çī¹åĪ«æĺ¯
    0.13
    çĦ¡è«ĸæĺ¯
    0.13
    _BOTH
    0.12
     обеиÑħ
    0.11
    both
    0.11
    either
    0.11
    Activations Density 0.318%

    No Known Activations