© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    of, growth, parents, linear, surface, tests

    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
    ichever
    -0.07
    prat
    -0.07
    èĵ
    -0.07
    ouser
    -0.07
     apprec
    -0.07
    enho
    -0.07
    illed
    -0.07
    aleb
    -0.07
    解梦
    -0.07
    ambu
    -0.06
    POSITIVE LOGITS
    -vers
    0.07
     Hor
    0.07
    以ä¸Ĭå°±æĺ¯å°ıç¼ĸ
    0.07
     meis
    0.07
    -role
    0.07
    .pdf
    0.06
    -I
    0.06
    客座
    0.06
    è°£
    0.06
    åıĤä¸İè¯Ħ论
    0.06
    Activations Density 0.138%

    No Known Activations