© 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. 26316
    Prev
    Next
    INDEX
    Explanations

    copy, modify, redistribute freely

    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
    egan
    -0.08
     invariably
    -0.07
    ÅĽwiad
    -0.07
    codes
    -0.07
    eria
    -0.07
     orchest
    -0.06
    assel
    -0.06
    èĥ½çĶ¨
    -0.06
    ettel
    -0.06
    åı¯åĪĨ为
    -0.06
    POSITIVE LOGITS
    åıªè¦ģä½ł
    0.13
    åıªè¦ģæĺ¯
    0.13
    ä½Ĩä¸įèĥ½
    0.13
    åıªè¦ģ
    0.12
    åıªè¦ģåľ¨
    0.12
     freely
    0.12
    åıªè¦ģæĪij们
    0.12
    åıªè¦ģèĥ½
    0.11
     impun
    0.11
     thoải
    0.11
    Activations Density 0.382%

    No Known Activations