© 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. 41597
    Prev
    Next
    INDEX
    Explanations

    sequences ending in n=

    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
    ানà§įত
    -0.08
    æľĿå¤ķ
    -0.08
    aczy
    -0.08
    ç»°
    -0.08
     obsta
    -0.07
    apo
    -0.07
    åįİé¾Ļ
    -0.07
    汶
    -0.07
    idou
    -0.07
    ìĦŃ
    -0.07
    POSITIVE LOGITS
    ocache
    0.08
    åĨħçĶŁ
    0.07
    æ±Łè¾¹
    0.07
    ertime
    0.07
    JI
    0.07
    _struct
    0.07
    ycz
    0.07
    å®ļæľŁçļĦ
    0.06
    crete
    0.06
    _JUMP
    0.06
    Activations Density 0.008%

    No Known Activations