© 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. 8122
    Prev
    Next
    INDEX
    Explanations

    `fixed`

    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
    ECH
    -0.08
    æĥ
    -0.07
    å±ħæĺĵ
    -0.07
    egner
    -0.07
    uD
    -0.07
    Structured
    -0.07
    awi
    -0.07
    ä¿ĥ
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
     submitting
    -0.06
    POSITIVE LOGITS
    åĽºå®ļçļĦ
    0.15
     fixed
    0.13
    åĽºå®ļ
    0.12
    fixed
    0.11
     Fixed
    0.11
     permanently
    0.11
    åĽºå®ļåľ¨
    0.10
    Fixed
    0.10
    æ°¸ä¹ħ
    0.10
    ãģĤãĤīãģĭãģĺãĤģ
    0.10
    Activations Density 0.391%

    No Known Activations