© 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. 22230
    Prev
    Next
    INDEX
    Explanations

    fill in the blank

    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
    lasan
    -0.07
     zab
    -0.06
    èijĹ
    -0.06
    çī¹çĤ¹
    -0.06
     Scr
    -0.06
    çļĦçī¹çĤ¹
    -0.06
    ique
    -0.06
    SK
    -0.06
    adopt
    -0.06
    _wr
    -0.06
    POSITIVE LOGITS
    使ä¹ĭ
    0.09
    ench
    0.09
     sentences
    0.08
    å®ĮåĸĦäºĨ
    0.08
    å®ĮæĪIJæĥħåĨµ
    0.08
     недоÑģÑĤа
    0.08
     ìĻĦìĦ±
    0.08
    å¡«åħ¥
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    å®Įæķ´
    0.08
    Activations Density 0.010%

    No Known Activations