© 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. 39366
    Prev
    Next
    INDEX
    Explanations

    findings, study, add, availability

    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
    comed
    -0.08
    regor
    -0.08
    anmar
    -0.08
    ENDA
    -0.08
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    çĪ±ä¸į
    -0.07
    mentos
    -0.07
    ekk
    -0.07
    çī¹æĸ°
    -0.07
    POSITIVE LOGITS
    ↵
    0.08
    ↵      ↵
    0.07
    ↵        ↵
    0.07
    ovol
    0.07
     pron
    0.06
    ↵        ↵        ↵
    0.06
    èıĮ
    0.06
    Ħ
    0.06
    iction
    0.06
    pay
    0.06
    Activations Density 0.030%

    No Known Activations