© 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. 14880
    Prev
    Next
    INDEX
    Explanations

    positioning and ordering

    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
    éķ¿çº¦
    -0.08
     lengths
    -0.08
    -length
    -0.08
    æķĻå·¥
    -0.08
    éķ¿åº¦çļĦ
    -0.08
    Length
    -0.07
    _lengths
    -0.07
    èĦ¸åŀĭ
    -0.07
    InstanceState
    -0.07
     Length
    -0.07
    POSITIVE LOGITS
     layer
    0.10
    å±Ĥ
    0.10
     Ñģлоем
    0.09
    åĽ¾å±Ĥ
    0.09
    å±Ĥ级
    0.09
     layers
    0.09
    層
    0.09
    (priority
    0.09
     priority
    0.09
    Priority
    0.09
    Activations Density 0.055%

    No Known Activations