© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34962
    Prev
    Next
    INDEX
    Explanations

    have to / need to

    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
    Negative Logits
    æĪijåľ¨è¿ĻéĩĮ
    -0.07
    kirchen
    -0.07
    ree
    -0.06
     distinguished
    -0.06
     possibly
    -0.06
    æĪij们çĶ¨
    -0.06
    на
    -0.06
    æĪijçĶ¨
    -0.06
    çķĻæĦı
    -0.06
    eline
    -0.06
    POSITIVE LOGITS
     must
    0.23
    å¿ħé¡»
    0.22
    must
    0.20
    å¿ħé¡»è¦ģ
    0.20
    å¿ħé¡»åľ¨
    0.20
    å¿ħé¡»æĺ¯
    0.20
     Must
    0.20
    å¿ħéłĪ
    0.19
     harus
    0.19
    å¿ħé¡»æľī
    0.19
    Activations Density 0.399%

    No Known Activations