© 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. 31134
    Prev
    Next
    INDEX
    Explanations

    angle, incidence, reflection

    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
     growth
    -0.07
    温
    -0.07
     Growth
    -0.06
    éĺ¶æ®µæĢ§
    -0.06
    ä¸į容
    -0.06
    缺
    -0.06
    éŁ³
    -0.06
    åħģ
    -0.06
    å®Įæķ´çļĦ
    -0.06
     weigh
    -0.06
    POSITIVE LOGITS
    åħ¥ç¤¾
    0.09
    decoded
    0.09
    ä¸įåħ¥
    0.09
    eson
    0.08
    ToDevice
    0.08
    ç§ij夫
    0.08
    -navigation
    0.08
    OMATIC
    0.08
    Įĵ
    0.08
    xis
    0.08
    Activations Density 0.003%

    No Known Activations