© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17567
    Prev
    Next
    INDEX
    Explanations

    key messages and insights

    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
    .exceptions
    -0.08
    iru
    -0.07
    irsi
    -0.07
    rsa
    -0.07
    åIJĥä¸ĢäºĽ
    -0.07
    汪æ´ĭ
    -0.06
    ivo
    -0.06
    ivio
    -0.06
    izio
    -0.06
    ÐŁÐŁ
    -0.06
    POSITIVE LOGITS
     takeaway
    0.07
    æł¸å¿ĥ
    0.07
    åħ³éĶ®çĤ¹
    0.07
     core
    0.07
    uen
    0.07
    /core
    0.07
     essentials
    0.07
    éĩįé»ŀ
    0.07
    Ta
    0.07
    è¦ģçĤ¹
    0.07
    Activations Density 0.004%

    No Known Activations