© 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. 2903
    Prev
    Next
    INDEX
    Explanations

    act 19xx

    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
    ári
    -0.07
    inas
    -0.07
    å¦ĤåĽł
    -0.07
    émat
    -0.07
    è¦ģä¹Īæĺ¯
    -0.07
    اÙħÙĨ
    -0.07
    ictured
    -0.07
    ipas
    -0.07
    åı¯è¨Ģ
    -0.07
    å¤Ħå¤Ħéķ¿
    -0.07
    POSITIVE LOGITS
    licer
    0.07
    iggins
    0.07
    onica
    0.06
    俱ä¹IJéĥ¨
    0.06
    åĽ½åºĵ
    0.06
    ä¾ĥ
    0.06
    egis
    0.06
     "
    0.06
    opa
    0.06
    Ùħع
    0.06
    Activations Density 0.056%

    No Known Activations