© 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. 22271
    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
    ovah
    -0.08
    ÑģÑı
    -0.08
    onnier
    -0.08
    çĸ¾çĹħé¢Ħéĺ²æݧåĪ¶ä¸Ńå¿ĥ
    -0.07
    polator
    -0.07
     teles
    -0.07
    ÑĤÑĥÑģ
    -0.07
    é¡¿äºĨ
    -0.07
    presse
    -0.07
    ulp
    -0.07
    POSITIVE LOGITS
    ieve
    0.07
     reck
    0.06
    arty
    0.06
    èģĤ
    0.06
    ftime
    0.06
    yun
    0.06
    ifest
    0.06
     ÑĥÑģÑĭ
    0.06
    ä¹ĭçªĹ
    0.06
    hab
    0.06
    Activations Density 0.000%

    No Known Activations