© 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. 43485
    Prev
    Next
    INDEX
    Explanations

    likewise, similarly, or ally

    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
    iosk
    -0.08
    aar
    -0.07
    rouw
    -0.07
    ezz
    -0.07
     appunto
    -0.07
    ermo
    -0.07
    orio
    -0.07
    icens
    -0.06
     Rig
    -0.06
     Bade
    -0.06
    POSITIVE LOGITS
    åľ¨äºº
    0.07
     similarly
    0.07
    å¯Ł
    0.07
    åIJĮä¸Ĭ
    0.07
    æĿ¡
    0.07
    ally
    0.06
    åıĪåĪ°äºĨ
    0.06
     likewise
    0.06
    为éĩį
    0.06
    _MIDDLE
    0.06
    Activations Density 0.085%

    No Known Activations