© 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. 23905
    Prev
    Next
    INDEX
    Explanations

    obstruction and compression

    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
    åıijåĪ°
    -0.08
    reck
    -0.07
     indul
    -0.07
     abst
    -0.07
    çĨł
    -0.07
    åıijæī¬
    -0.07
    åħī大
    -0.06
     вÑģп
    -0.06
    .reflect
    -0.06
    .rmi
    -0.06
    POSITIVE LOGITS
    åİĭè¿«
    0.14
     obstruction
    0.13
     obstruct
    0.12
    æ¢Ĺéĺ»
    0.12
    éĺ»å¡ŀ
    0.11
    _blocking
    0.10
    åłµå¡ŀ
    0.10
    æĮ¤åİĭ
    0.10
     Ñģда
    0.10
    ä¸įéĢļ
    0.09
    Activations Density 0.217%

    No Known Activations