© 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. 51190
    Prev
    Next
    INDEX
    Explanations

    references to other works

    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
    ì§ĢìĻĢ
    -0.06
    æļĩ
    -0.06
    æĬ¹
    -0.06
    翼翼
    -0.06
    åIJĽ
    -0.06
    çĪ·
    -0.06
    åħ¬åŃIJ
    -0.06
    éĽĦ
    -0.06
    Exception
    -0.06
     da
    -0.06
    POSITIVE LOGITS
    /*@
    0.09
    éĺIJ
    0.08
    sgi
    0.08
    ilog
    0.08
    èĢĮéĻį
    0.07
    å°ĨæĮīçħ§
    0.07
    åħ±è¿Ľ
    0.07
    缩
    0.07
    memberof
    0.07
    .actual
    0.07
    Activations Density 0.081%

    No Known Activations