© 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. 18510
    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
    noinspection
    -0.08
    ansch
    -0.07
    涯
    -0.07
    åįĩåĪĿ
    -0.07
    scriber
    -0.07
    /*/
    -0.07
    æłĩå®ļ
    -0.06
     Expanded
    -0.06
    ATTR
    -0.06
    ulong
    -0.06
    POSITIVE LOGITS
    hirt
    0.07
    åĨ
    0.07
    aison
    0.07
    bog
    0.07
    ç¼Ń
    0.07
    纽
    0.07
    åĬ
    0.07
    acial
    0.07
    ãģĺãĤģãģ¦
    0.07
    强弱
    0.07
    Activations Density 0.000%

    No Known Activations