© 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. 28183
    Prev
    Next
    INDEX
    Explanations

    learn, idols, cuyler, fully, molding

    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
    aik
    -0.06
    usc
    -0.06
    å§IJ妹
    -0.06
    ç¿
    -0.06
    çĨĬ
    -0.06
    ä»Ĭå¤ľ
    -0.06
    ±
    -0.06
    èĬŃ
    -0.06
     FIXME
    -0.05
    å¤ıå¨ģ夷
    -0.05
    POSITIVE LOGITS
    dae
    0.08
    ç½ijç«Ļ导èĪª
    0.08
    ¼
    0.08
    uel
    0.08
    ufen
    0.08
    çĽĺ
    0.08
    åĨ³
    0.07
    ifique
    0.07
    dsa
    0.07
     диÑģÑĨипли
    0.07
    Activations Density 0.160%

    No Known Activations