© 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. 56565
    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
    chnik
    -0.08
    æī¿
    -0.08
    ãĥ¼ãĥĦ
    -0.08
    ä¸ĢåĪ»
    -0.08
    verty
    -0.08
    atomy
    -0.08
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.08
    okka
    -0.08
     Calon
    -0.07
    ynet
    -0.07
    POSITIVE LOGITS
    d
    0.07
    dor
    0.07
    åIJij她
    0.07
    åĽłä¸ºåħ¶
    0.06
    mel
    0.06
    oto
    0.06
    du
    0.06
    å®°
    0.06
     repar
    0.06
     revi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.