© 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. 39799
    Prev
    Next
    INDEX
    Explanations

    mapping matched

    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
    çĵ®
    -0.07
    ĤŃ
    -0.07
    æĿī
    -0.07
    é¾
    -0.06
    éĢIJ级
    -0.06
     uns
    -0.06
     levels
    -0.06
    屡
    -0.06
    æĪ
    -0.06
    åıĤ
    -0.06
    POSITIVE LOGITS
     nonatomic
    0.08
    ölt
    0.08
    msp
    0.08
    sampling
    0.08
     sampled
    0.08
    Sampling
    0.08
    ielt
    0.08
    AMI
    0.08
     sampling
    0.07
     Sampling
    0.07
    Activations Density 0.015%

    No Known Activations