© 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. 64183
    Prev
    Next
    INDEX
    Explanations

    without certain conditions or outcomes

    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
    ä¾
    -0.08
    ä¸į失
    -0.07
    .timing
    -0.06
     Braga
    -0.06
     Mund
    -0.06
    .runners
    -0.06
    èIJ±
    -0.06
    æŁij
    -0.06
    yclopedia
    -0.06
    æĹł
    -0.06
    POSITIVE LOGITS
    çī¹åĪ«è¯´æĺİ
    0.08
    proper
    0.08
    çī¹åĪ«å£°æĺİ
    0.07
     Mancha
    0.07
    voud
    0.07
     proper
    0.07
    additional
    0.07
    æľīä¸Ģçķª
    0.07
    ecessarily
    0.07
     Kenntnis
    0.07
    Activations Density 0.111%

    No Known Activations