© 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. 39349
    Prev
    Next
    INDEX
    Explanations

    often, usually, believed, supposed, typically

    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
    举
    -0.08
    å±ĬæŶ
    -0.07
    terer
    -0.07
    ä½ĻçĶŁ
    -0.07
    ques
    -0.07
    ặng
    -0.07
     magari
    -0.07
    å¯Ħ
    -0.07
    温
    -0.07
    ore
    -0.06
    POSITIVE LOGITS
     notoriously
    0.12
     famously
    0.11
    oriously
    0.10
    çĶ±äºİåħ¶
    0.10
    被认为æĺ¯
    0.09
    åħ¬è®¤
    0.08
    æĬ¥éģĵ称
    0.08
     reported
    0.08
    åı·ç§°
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    Activations Density 0.048%

    No Known Activations