© 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. 2175
    Prev
    Next
    INDEX
    Explanations

    database interaction

    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
    sic
    -0.07
    å·§
    -0.07
     (“
    -0.06
    yam
    -0.06
    åħĥ
    -0.06
    äºĨä¸Ģä¼ļ
    -0.06
    iesa
    -0.06
    ancy
    -0.06
    å±±ä¹ĭ
    -0.06
    _CON
    -0.06
    POSITIVE LOGITS
     flagr
    0.07
    Į¨
    0.07
    _SID
    0.07
    igan
    0.07
    à´ļàµįà´ļàµį
    0.07
    éĹ´çĽĺ
    0.07
    缴æİ¥åIJij
    0.07
    pera
    0.07
    Ñħова
    0.07
    igator
    0.07
    Activations Density 0.031%

    No Known Activations