© 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. 3484
    Prev
    Next
    INDEX
    Explanations

    if / when clauses

    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
    èĨ
    -0.07
     tre
    -0.07
    uild
    -0.07
    quete
    -0.06
    rophe
    -0.06
    ajaran
    -0.06
    并ä¸į代表
    -0.06
    stm
    -0.06
    askell
    -0.06
    à¹Ģà¸Ĺ
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.10
     hingegen
    0.09
     наобоÑĢоÑĤ
    0.09
    åħ·ä½ĵæŶéĹ´
    0.09
    åĪĻ为
    0.08
    åĪĻ
    0.08
    å¹²èĦĨ
    0.08
    åħ¶ä»ĸçļĦ
    0.08
    åĪĻæĺ¯
    0.08
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
    Activations Density 0.025%

    No Known Activations