© 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. 57209
    Prev
    Next
    INDEX
    Explanations

    technical functions and cars

    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
    èıģ
    -0.07
    ulp
    -0.07
    æĿİæĻĵ
    -0.06
    imm
    -0.06
     imm
    -0.06
    gleich
    -0.06
     Blan
    -0.06
    æĪij社
    -0.06
    使çĶ¨æĿĥ
    -0.06
    Imm
    -0.06
    POSITIVE LOGITS
    æĶ¯
    0.08
    upe
    0.08
    athers
    0.08
    vine
    0.08
    artin
    0.07
    ouncer
    0.07
    arth
    0.07
    ardi
    0.07
    _SELECTOR
    0.07
     Rut
    0.07
    Activations Density 0.002%

    No Known Activations