© 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. 61274
    Prev
    Next
    INDEX
    Explanations

    path separators and code structures

    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
    æĤĦ
    -0.08
    å±ł
    -0.07
    ade
    -0.06
    ist
    -0.06
    举
    -0.06
    lname
    -0.06
    ara
    -0.06
    ik
    -0.06
    ip
    -0.06
    dia
    -0.06
    POSITIVE LOGITS
    anken
    0.08
    _BODY
    0.08
    zos
    0.08
    habi
    0.08
    ctp
    0.08
    ázat
    0.07
    对ä¸Ĭè¿°
    0.07
    apel
    0.07
     body
    0.07
     BMC
    0.07
    Activations Density 0.024%

    No Known Activations