© 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. 25323
    Prev
    Next
    INDEX
    Explanations

    deliberately done causing impact

    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
     %#
    -0.08
    åıªè¦ģèĥ½
    -0.08
    utherland
    -0.08
    èĩªå·±çĭ¬çī¹çļĦ
    -0.07
     bá»ķng
    -0.07
    avn
    -0.07
     ÏĥÏħνα
    -0.07
    Ĩµ
    -0.07
    bru
    -0.07
    icum
    -0.07
    POSITIVE LOGITS
     deliberately
    0.14
    åĪ»æĦı
    0.14
     deliberate
    0.14
    å¹²é¢Ħ
    0.14
    人为
    0.14
     consciously
    0.13
     intervention
    0.13
    æķħæĦı
    0.13
    æķħæĦıçļĦ
    0.12
     intentionally
    0.12
    Activations Density 0.173%

    No Known Activations