© 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. 37884
    Prev
    Next
    INDEX
    Explanations

    if condition logic

    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
    .hex
    -0.07
    Hex
    -0.06
    OrCreate
    -0.06
    Forever
    -0.06
    /at
    -0.06
    èĻı
    -0.06
    宣读
    -0.06
     whereas
    -0.06
    adh
    -0.06
     dagegen
    -0.06
    POSITIVE LOGITS
    æ´»
    0.08
    积æŀģè¿Ľåıĸ
    0.08
    trs
    0.08
    ikle
    0.07
     акÑĤивноÑģÑĤи
    0.07
    æ¤Ĵ
    0.07
    cif
    0.07
    åıĺ
    0.07
    ikus
    0.07
    å½ĵçĦ¶äºĨ
    0.07
    Activations Density 0.165%

    No Known Activations