© 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. 8943
    Prev
    Next
    INDEX
    Explanations

    citations like [@kpz3]

    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
    ä¸ĭ
    -0.06
    ģ
    -0.06
    I
    -0.06
    åİŁä»¶åıĬå¤įåį°ä»¶
    -0.06
    ehm
    -0.06
    ajs
    -0.06
    {}
    -0.06
    inent
    -0.06
    igur
    -0.06
    pun
    -0.05
    POSITIVE LOGITS
    triz
    0.09
    å°±æĺ¯æĪij
    0.08
    çĤľ
    0.08
    undler
    0.08
    pper
    0.08
    inds
    0.08
    ypes
    0.07
    िता
    0.07
    ä½łæĺ¯è°ģ
    0.07
    dsn
    0.07
    Activations Density 0.163%

    No Known Activations