© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12055
    Prev
    Next
    INDEX
    Explanations

    code and punctuation boundaries

    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
    -0.06
    å®ĩ
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    èĢĮæĹł
    -0.05
    微信æī«ä¸Ģæī«
    -0.05
    ussin
    -0.05
    Äįi
    -0.05
    åį§åºĬ
    -0.05
    åĹ¡åĹ¡
    -0.05
    ½
    -0.05
    POSITIVE LOGITS
    haps
    0.08
    oman
    0.08
    ewnÄĻ
    0.08
    ä¾ĽåĽ¾
    0.08
    oces
    0.07
    esome
    0.07
    à¹Īà¸Ńย
    0.07
    اتÙĩ
    0.07
    pector
    0.07
    iras
    0.07
    Activations Density 0.343%

    No Known Activations