© 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. 20864
    Prev
    Next
    INDEX
    Explanations

    guide and guiding processes

    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
    دÙĬÙĪ
    -0.07
     lẻ
    -0.06
    plier
    -0.06
    çĪĨåıij
    -0.06
    æ®Ĭèį£
    -0.06
     tê
    -0.06
    acker
    -0.06
    akk
    -0.06
    ities
    -0.06
    olation
    -0.05
    POSITIVE LOGITS
     toward
    0.12
    æĮĩå¼ķ
    0.11
     towards
    0.11
     ÙĨØŃÙĪ
    0.10
    posts
    0.10
    à¹Ħà¸Ľà¸ªà¸¹à¹Ī
    0.10
     hacia
    0.10
    گرÛĮ
    0.10
    å¼ķ导
    0.10
    guide
    0.09
    Activations Density 0.109%

    No Known Activations