© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26903
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
     rather
    -0.07
    èĢĮä¸įæĺ¯
    -0.07
    ä¸įå¿ħ
    -0.07
    ä½Ĩæĺ¯å®ĥ
    -0.07
    è¿ĺèĥ½å¤Ł
    -0.07
     ÑıкобÑĭ
    -0.06
    ä¸įæĺ¯è¯´
    -0.06
    è¿ĺä¸įæĺ¯
    -0.06
    ountains
    -0.06
    çĤ¹æѤ
    -0.06
    POSITIVE LOGITS
    ä½ľåĪĻ
    0.11
    åĪĻéľĢè¦ģ
    0.10
    åĪĻè¦ģ
    0.09
    åĪĻæĺ¯
    0.09
    ãģĿãģĨãģ§
    0.09
     hingegen
    0.08
    åĪĻä¼ļ
    0.08
    åĪĻçĶ±
    0.08
     dagegen
    0.08
    åĪĻåı¯ä»¥
    0.08
    Activations Density 0.095%

    No Known Activations