© 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. 61030
    Prev
    Next
    INDEX
    Explanations

    join, reduce, string operations

    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
    ä¸į讲
    -0.07
    еÑīа
    -0.07
    ep
    -0.07
    ity
    -0.06
    ä¸įæIJŀ
    -0.06
    ä¸įèĻļ
    -0.06
     C
    -0.06
     A
    -0.06
    p
    -0.06
    onge
    -0.06
    POSITIVE LOGITS
    çĿ¦
    0.08
    lashes
    0.08
    åħ¨å®¶
    0.08
    estet
    0.08
    rema
    0.08
     Produc
    0.08
    IMIT
    0.08
     concaten
    0.08
    венÑĤа
    0.08
    ÙĪÙĨد
    0.08
    Activations Density 0.010%

    No Known Activations