© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19638
    Prev
    Next
    INDEX
    Explanations

    dates and references

    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
     matrimoniale
    -0.08
    inach
    -0.08
    管å±Ģ
    -0.08
    æĬĬäºĭæĥħ
    -0.08
    è¾ħ
    -0.08
    åĸĩ
    -0.08
    istrar
    -0.07
    gef
    -0.07
    ä¸ĭæŀ¶
    -0.07
    roud
    -0.07
    POSITIVE LOGITS
     ble
    0.07
    çĻ½éľ²
    0.06
    ħ
    0.06
    اÙĦÙĬ
    0.06
    çĴĭ
    0.06
    ä¹ħ
    0.06
    çĻ½æ°´
    0.06
    ÑĤÑİ
    0.06
    est
    0.06
    èģŀ
    0.06
    Activations Density 0.230%

    No Known Activations