© 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. 56409
    Prev
    Next
    INDEX
    Explanations

    "value" after punctuation

    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
    éĥijéĩį声æĺİ
    -0.08
    gaard
    -0.06
     natives
    -0.06
    aka
    -0.06
    大æĥĬ
    -0.06
    ä¸Ģ带
    -0.06
    OWN
    -0.06
    enic
    -0.06
    ulls
    -0.06
     Aren
    -0.06
    POSITIVE LOGITS
     Verse
    0.09
     Abed
    0.08
    é«
    0.08
     izle
    0.08
    Verse
    0.08
    éĩįå¤į
    0.08
    _REPEAT
    0.08
    erald
    0.07
    ipeline
    0.07
    serter
    0.07
    Activations Density 0.005%

    No Known Activations