© 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. 22172
    Prev
    Next
    INDEX
    Explanations

    cause or pathway

    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
    leb
    -0.07
    çŃīæݪæĸ½
    -0.07
    çĶ¨éĢĶ
    -0.07
    éħįå¥Ĺ
    -0.07
    çĶ¨å¤Ħ
    -0.07
    æľīä»Ģä¹ĪçĶ¨
    -0.07
     ÐĿеÑĢе
    -0.07
    å¥ĩæĢª
    -0.07
    è¿Ļç§įåģļæ³ķ
    -0.07
     legal
    -0.07
    POSITIVE LOGITS
    主è¦ģ表çݰ为
    0.10
    æīĢèĩ´
    0.09
    åı¯å¯¼èĩ´
    0.09
    å¤ļè§ģäºİ
    0.09
    导èĩ´çļĦ
    0.08
    çĹħç¨ĭ
    0.08
    æľĢ常è§ģ
    0.08
     manifestations
    0.08
     manifestation
    0.08
    åħĪéĶĭ模èĮĥ
    0.08
    Activations Density 0.006%

    No Known Activations