© 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. 28580
    Prev
    Next
    INDEX
    Explanations

    abnormal conditions, prognosis, or development

    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
    averse
    -0.06
    ÙĪرÙĪ
    -0.06
    æ¯Ķ以å¾Ģ
    -0.06
    æĮĩ导ä¸ĭ
    -0.06
    çķĻ
    -0.06
    çī¹åĪ«
    -0.06
    .dat
    -0.06
    çłĶ究åĪ¶å®ļ
    -0.06
    atha
    -0.06
    schung
    -0.06
    POSITIVE LOGITS
    çĶ±æĸ¼
    0.12
    åĽłä¸ºæľī
    0.12
     because
    0.12
    çĶ±äºİåħ¶
    0.11
    åĽłçĤº
    0.11
    åĽłçĪ²
    0.11
    åĽłä¸ºè¿ĻäºĽ
    0.11
    because
    0.11
    çĶ±äºİ
    0.10
    åĽłä¸ºåľ¨
    0.10
    Activations Density 0.025%

    No Known Activations