© 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. 30793
    Prev
    Next
    INDEX
    Explanations

    capital, assets, resources

    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
    èģĮå®Ī
    -0.08
    表éĿ¢å¤ĦçIJĨ
    -0.08
     tanggung
    -0.07
    eno
    -0.07
    çīº
    -0.07
    çİĩè¾¾åĪ°
    -0.07
    æľĢçĥŃ
    -0.07
    å®īåħ¨çĽij管
    -0.07
    amil
    -0.07
     Prij
    -0.07
    POSITIVE LOGITS
     assets
    0.11
     valuable
    0.10
     usable
    0.10
    å®Ŀè´µ
    0.10
     accumulated
    0.10
    ç¦Ģ
    0.10
     invaluable
    0.10
    å®Ŀè´µçļĦ
    0.10
     amassed
    0.10
     asset
    0.10
    Activations Density 0.018%

    No Known Activations