© 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. 8990
    Prev
    Next
    INDEX
    Explanations

    pivot, axis, hinge

    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
    -0.07
     Semen
    -0.06
     normalized
    -0.06
    lang
    -0.06
    éĻĦåĴĮ
    -0.06
    åıįæĺł
    -0.06
     Reflect
    -0.06
     Vej
    -0.06
    tid
    -0.06
    èĩªåĬ©
    -0.06
    POSITIVE LOGITS
    æĶ¯çĤ¹
    0.10
    åĽºå®ļçļĦ
    0.10
    çĤ¹è¿Ľè¡Į
    0.09
    åŁºçĤ¹
    0.08
    çĤ¹æĺ¯
    0.08
    åĽºå®ļ
    0.08
    åĸľéĹ»
    0.08
    åĪ©çī©
    0.08
     Oaks
    0.08
    á»ķ
    0.08
    Activations Density 0.011%

    No Known Activations