© 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. 64268
    Prev
    Next
    INDEX
    Explanations

    redundant, useless, or unnecessary

    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
    etype
    -0.08
    heim
    -0.08
    åħ¬è®¤çļĦ
    -0.07
    insic
    -0.07
    åIJ´æ±Ł
    -0.07
     JMP
    -0.07
    çł°çł°
    -0.07
    缺
    -0.07
    ertype
    -0.07
    ç¼
    -0.07
    POSITIVE LOGITS
     unnecessary
    0.11
     inutile
    0.10
     useless
    0.10
     irrelevant
    0.10
    æľīçĶ¨
    0.10
    æľīä»Ģä¹ĪçĶ¨
    0.09
     unnecessarily
    0.09
     pointless
    0.09
    æĹłçĶ¨
    0.09
     redundant
    0.08
    Activations Density 0.067%

    No Known Activations