© 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. 29960
    Prev
    Next
    INDEX
    Explanations

    plasma

    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
     merc
    -0.07
    ä¸İèĩªçĦ¶
    -0.07
    мам
    -0.06
    èĥŀèĥİ
    -0.06
    aes
    -0.06
    lix
    -0.06
    pir
    -0.06
    åĽ½å®¶å¯¹
    -0.06
     sen
    -0.06
    ijat
    -0.06
    POSITIVE LOGITS
    asma
    0.09
    onda
    0.08
    å±Ģåľ°
    0.08
     dynamics
    0.08
    incipal
    0.08
    åѦæ³ķ
    0.08
     turbulence
    0.08
    ç»ĩ女
    0.07
     sma
    0.07
    omid
    0.07
    Activations Density 0.025%

    No Known Activations