© 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. 45725
    Prev
    Next
    INDEX
    Explanations

    Tomography

    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
     Corso
    -0.09
    aa
    -0.07
    PTR
    -0.07
    天ä¸ĭ
    -0.07
    çĮİ
    -0.06
    èµĸ
    -0.06
    çĽ¾
    -0.06
    _fd
    -0.06
    ä¸Ĭä¸ĢæĿ¡
    -0.06
    ç¼Ĩ
    -0.06
    POSITIVE LOGITS
    rna
    0.08
    éĽ¨éľ²
    0.08
     buc
    0.07
    angkalan
    0.07
    amenta
    0.07
    rement
    0.07
    _SDK
    0.07
    orum
    0.07
    AccessException
    0.07
    缸åħ³ä¼ģä¸ļ
    0.07
    Activations Density 0.180%

    No Known Activations