© 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. 27877
    Prev
    Next
    INDEX
    Explanations

    states perception and reports

    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
    udos
    -0.07
     revis
    -0.06
    éĢļçŁ¥ä¹¦
    -0.06
    جب
    -0.06
    ikka
    -0.06
    çļĦåĪ¶åº¦
    -0.06
    OTS
    -0.06
     proc
    -0.05
    åı«
    -0.05
     PL
    -0.05
    POSITIVE LOGITS
    åľ¨æīĢ
    0.09
    ÙĦÙĪÙĦ
    0.08
    llib
    0.08
    ç¬Ķä¸ĭçļĦ
    0.08
    inales
    0.08
    åħ¶è§ĤçĤ¹
    0.08
    çļĦæĸ¹å¼ıæĿ¥
    0.08
    ihal
    0.08
     deem
    0.08
    _MA
    0.08
    Activations Density 0.040%

    No Known Activations