© 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. 41376
    Prev
    Next
    INDEX
    Explanations

    attitudes, feelings, perceptions, beliefs

    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
     caos
    -0.08
    æĬ¡
    -0.07
    æ±Ĺ
    -0.07
    å¥Ħ
    -0.07
     ÑĢазÑĢе
    -0.07
     controvers
    -0.07
    æĽ¿å°¼
    -0.07
    itele
    -0.07
     interoper
    -0.07
    踪
    -0.06
    POSITIVE LOGITS
    æĢģ
    0.11
    信念
    0.10
    çIJĨæĢ§
    0.10
    æ·¡æ¼ł
    0.10
    çIJĨæĻº
    0.10
     beliefs
    0.10
     motivations
    0.09
    驱使
    0.09
    强çĥĪçļĦ
    0.09
     subconscious
    0.09
    Activations Density 0.202%

    No Known Activations