© 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. 11887
    Prev
    Next
    INDEX
    Explanations

    past events and decisions

    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
    çģ«ä¸Ĭ
    -0.08
     classic
    -0.07
    .wik
    -0.06
     Diz
    -0.06
    .bz
    -0.06
    wend
    -0.06
    åĽłåħ¶
    -0.06
    classic
    -0.06
    çĭ¸
    -0.06
    jure
    -0.06
    POSITIVE LOGITS
    å·²æľī
    0.11
     already
    0.11
    å·²ç»ıåľ¨
    0.11
    çİ°æľīçļĦ
    0.11
    å·²æľīçļĦ
    0.11
    缮åīįå·²
    0.11
     reportedly
    0.11
    缮åīį没æľī
    0.11
    类似éĹ®é¢ĺ
    0.10
    already
    0.10
    Activations Density 0.331%

    No Known Activations