© 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. 3385
    Prev
    Next
    INDEX
    Explanations

    construction projects

    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
    ä»»åħį
    -0.07
    å®ĪåĪĻ
    -0.06
    æĹłæĦıä¸Ń
    -0.06
    å´©
    -0.06
     routines
    -0.06
     unwitting
    -0.06
    åĩłåĪĨ
    -0.06
    å®Ī
    -0.06
     hierarchy
    -0.06
     LGBTQ
    -0.06
    POSITIVE LOGITS
    å®Įå·¥
    0.13
    çŃīé¡¹çĽ®
    0.11
    é¡¹çĽ®ä¸Ń
    0.11
     planned
    0.10
     slated
    0.10
    æĮī计åĪĴ
    0.10
    å®ĮæĪIJåIJİ
    0.10
    è¯¥é¡¹çĽ®
    0.10
    äºĮæľŁ
    0.10
    è§Ħ模为
    0.10
    Activations Density 0.441%

    No Known Activations