© 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. 10574
    Prev
    Next
    INDEX
    Explanations

    image paths ending with _black

    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
    ollo
    -0.08
    çĦ¶å¤§
    -0.08
    IPP
    -0.07
    ide
    -0.07
    ipp
    -0.07
    å¹³çĶŁ
    -0.07
    aha
    -0.07
     conto
    -0.07
    çĶŁçļĦ
    -0.07
    oya
    -0.07
    POSITIVE LOGITS
    ëŀĦ
    0.07
     titular
    0.07
    ä»ij
    0.06
    èī¯
    0.06
    伦
    0.06
    edas
    0.06
    å°ĨæĪij
    0.06
    åĺ´
    0.06
    .rec
    0.06
    ugal
    0.06
    Activations Density 0.003%

    No Known Activations