© 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. 19805
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    رائ
    -0.08
    ÏĪε
    -0.07
    ropole
    -0.07
    ornings
    -0.07
    gorithm
    -0.07
    resents
    -0.07
    osexual
    -0.07
    RED
    -0.07
    çļĦå°±
    -0.07
    èĩªåıij
    -0.07
    POSITIVE LOGITS
     Ibid
    0.08
    åıĤè§ģ
    0.07
    åľ¨è¿Ļæł·çļĦ
    0.07
    大çĪ±
    0.07
     www
    0.07
    abet
    0.06
    see
    0.06
    vgl
    0.06
    å°¬
    0.06
     see
    0.06
    Activations Density 0.214%

    No Known Activations