© 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. 50137
    Prev
    Next
    INDEX
    Explanations

    more developed, young children, other people

    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¸īå¹´æĿ¥
    -0.07
    åıijå±ķä¸İ
    -0.07
    graphic
    -0.07
    nob
    -0.07
    çĶ°
    -0.07
    çŀŃ
    -0.07
    æ¯ĶæĻ®éĢļ
    -0.07
    ãĥīãĥ³
    -0.07
    åĪ°å°¾
    -0.07
    ppard
    -0.07
    POSITIVE LOGITS
    çĥ¨
    0.07
    æĸŃå±Ĥ
    0.07
    artes
    0.07
    شت
    0.06
    åĿıå¤Ħ
    0.06
     Grau
    0.06
    éĻħ
    0.06
     bom
    0.06
    åıĤä¸İåħ¶ä¸Ń
    0.06
    çīĽæİĴ
    0.06
    Activations Density 0.150%

    No Known Activations