© 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. 61592
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ains
    -0.07
    (
    -0.07
    ей
    -0.06
    强弱
    -0.06
    ä»İè½»
    -0.06
    ÑĮÑı
    -0.06
    ä»İéĩį
    -0.06
    ¿
    -0.06
    оÑģÑĤ
    -0.06
     aud
    -0.06
    POSITIVE LOGITS
    coni
    0.09
    icode
    0.08
    rowse
    0.08
    åħĭåħ°
    0.08
    ÑĤÑĢом
    0.07
    åĸĿä¸ĢæĿ¯
    0.07
    mite
    0.07
    mals
    0.07
    cles
    0.07
     FUNCT
    0.07
    Activations Density 0.000%

    No Known Activations