© 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. 60986
    Prev
    Next
    INDEX
    Explanations

    resist, temptation, help, impulses

    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
    çĴĭ
    -0.08
    vag
    -0.08
    è§ģæĪij
    -0.08
    abase
    -0.07
    OBO
    -0.07
    äºĨä¸įèµ·
    -0.07
    å¾Ĺåħ¶
    -0.07
    ovas
    -0.07
    èĬ³èįī
    -0.07
    ope
    -0.07
    POSITIVE LOGITS
    å¿įä¸įä½ı
    0.11
     temptation
    0.11
    åĨ²åĬ¨
    0.10
    ä¸įçĶ±èĩªä¸»
    0.10
    æĥħä¸įèĩªç¦ģ
    0.10
    ä¸įèĩªè§ī
    0.09
     tempted
    0.09
     impulses
    0.09
     urge
    0.09
    tempt
    0.09
    Activations Density 0.257%

    No Known Activations