© 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. 50782
    Prev
    Next
    INDEX
    Explanations

    starting code blocks

    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
    ib
    -0.07
    çİ°éĺ¶æ®µ
    -0.07
    ²
    -0.07
    adb
    -0.07
    odge
    -0.07
    ียà¸ļ
    -0.06
    adol
    -0.06
    æ¶ĪçĤİ
    -0.06
    å®ŀçİ°çļĦ
    -0.06
    åłĤ
    -0.06
    POSITIVE LOGITS
    èµ·å§ĭ
    0.10
    èµ·çĤ¹
    0.09
    .Factory
    0.08
    START
    0.08
    å¼Ģå§ĭçļĦ
    0.07
     Classification
    0.07
     starting
    0.07
    åĩºåıijçĤ¹
    0.07
    Classification
    0.07
    -init
    0.07
    Activations Density 0.010%

    No Known Activations