© 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. 38650
    Prev
    Next
    INDEX
    Explanations

    Schrödinger equation / satisfied when

    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
     آباد
    -0.08
    INLINE
    -0.08
    ktop
    -0.07
    reno
    -0.07
    stay
    -0.07
     táºŃn
    -0.07
    ä¸įåĪĨ
    -0.07
    ollo
    -0.07
    wi
    -0.06
    бин
    -0.06
    POSITIVE LOGITS
    å¿ħ须符åIJĪ
    0.09
     consistency
    0.09
     satisfying
    0.08
    ä¸Ģèĩ´æĢ§
    0.08
    满足
    0.08
    满足äºĨ
    0.08
     coincidence
    0.08
    èĥ½æ»¡è¶³
    0.07
     hod
    0.07
    egos
    0.07
    Activations Density 0.004%

    No Known Activations