© 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. 17941
    Prev
    Next
    INDEX
    Explanations

    radical and chemical suffixes

    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
    IU
    -0.08
    åħ¬å¸ĥ
    -0.07
    åı¯ä»¥çĶ±
    -0.07
    seh
    -0.06
    追
    -0.06
    OSA
    -0.06
    åľ°ä½¿çĶ¨
    -0.06
     publicly
    -0.06
    mena
    -0.06
    å¿ĺæĢĢ
    -0.06
    POSITIVE LOGITS
    ingham
    0.09
    æĪĸåħ¶
    0.08
    éĩĬæĶ¾åĩº
    0.08
    -relative
    0.08
    æĸĽ
    0.08
     pró
    0.08
     molecule
    0.08
    enthal
    0.07
    äºīå½ĵ
    0.07
    atum
    0.07
    Activations Density 0.023%

    No Known Activations