© 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. 22472
    Prev
    Next
    INDEX
    Explanations

    positive and directional words

    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
    å·¥ä½ľçļĦéĩįè¦ģ
    -0.07
    为äºĨæĽ´å¥½åľ°
    -0.06
    ç°
    -0.06
    åľĪçļĦ
    -0.06
     proximity
    -0.06
    ibro
    -0.06
    è¿ľè¿ij
    -0.06
    ocard
    -0.06
    é§IJ
    -0.06
    èİī
    -0.06
    POSITIVE LOGITS
    åIJijåı³
    0.10
     pozitiv
    0.10
     positivo
    0.10
     Positive
    0.10
     positive
    0.10
    positive
    0.10
    为æŃ£
    0.09
    Positive
    0.09
     positivas
    0.09
     positiva
    0.09
    Activations Density 0.028%

    No Known Activations