© 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. 49620
    Prev
    Next
    INDEX
    Explanations

    zero or 0

    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
    è¿ĶåĽŀ顶éĥ¨
    -0.09
    ibel
    -0.08
    idis
    -0.08
    åѦåĪ°äºĨå¾Īå¤ļ
    -0.08
    à¸ļาà¸Ķ
    -0.07
    .Slice
    -0.07
    å¥ī
    -0.07
    ÎŃλ
    -0.07
     Claro
    -0.07
    iforn
    -0.07
    POSITIVE LOGITS
    å¨ħ
    0.07
    Grace
    0.07
    multiple
    0.06
     multiple
    0.06
    çĤ¹æĺ¯
    0.06
    بط
    0.06
     Sebastian
    0.06
    ä¸įæĺ¯åĽłä¸º
    0.06
    ä½Ĩåħ¶
    0.06
    èĢĥè¯ķ大纲
    0.06
    Activations Density 0.005%

    No Known Activations