© 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. 48497
    Prev
    Next
    INDEX
    Explanations

    amplification and concentration

    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
    太è¿ĩäºİ
    -0.07
    outh
    -0.07
    ertoire
    -0.07
    æļĸæļĸçļĦ
    -0.07
    以éĺ²æŃ¢
    -0.07
    ç«ĭæĸ°
    -0.07
    chnitt
    -0.06
     boundaries
    -0.06
    lah
    -0.06
     PREV
    -0.06
    POSITIVE LOGITS
    æĶ¾å¤§
    0.15
     ampl
    0.15
     amplify
    0.13
    åĢįæķ°
    0.13
    çĻ¾åĢį
    0.12
     Ampl
    0.12
     amplified
    0.11
    åįģåĢį
    0.11
    åĢį
    0.10
     magn
    0.10
    Activations Density 0.062%

    No Known Activations