© 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. 20021
    Prev
    Next
    INDEX
    Explanations

    implementation description

    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
    oin
    -0.08
    anol
    -0.07
    å·¥ç¨ĭæ¡Īä¾ĭ
    -0.07
    RequestParam
    -0.07
    reif
    -0.07
    _pag
    -0.07
    _intr
    -0.06
    .toJSON
    -0.06
    èĻ
    -0.06
    太快
    -0.06
    POSITIVE LOGITS
     Approach
    0.07
    ndx
    0.07
     Address
    0.07
     approach
    0.06
    èģ·
    0.06
    typed
    0.06
    unicode
    0.06
    zg
    0.06
    çĶµèĦijä¸Ĭ
    0.06
    çĿĢä½ł
    0.06
    Activations Density 0.007%

    No Known Activations