© 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. 8777
    Prev
    Next
    INDEX
    Explanations

    grouping into experimental groups

    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
     commonly
    -0.07
    _pad
    -0.06
    æīĢçŁ¥
    -0.06
    capital
    -0.06
     facial
    -0.06
    fragment
    -0.06
    åħĪéĶĭ模èĮĥ
    -0.06
     ngu
    -0.06
     http
    -0.06
    éĢļçĶ¨çļĦ
    -0.06
    POSITIVE LOGITS
    对çħ§ç»Ħ
    0.14
    对çħ§
    0.11
    å®ŀéªĮ
    0.09
    -controls
    0.08
    对æ¯Ķ
    0.08
     experimental
    0.08
    atoon
    0.08
    ifax
    0.08
     Kontrol
    0.08
    abora
    0.08
    Activations Density 0.416%

    No Known Activations