© 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. 4142
    Prev
    Next
    INDEX
    Explanations

    via or through

    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
     independently
    -0.07
     Enumeration
    -0.07
     outright
    -0.07
    è§ģçĬ¶
    -0.06
    å«£
    -0.06
     independ
    -0.06
     independent
    -0.06
    æīĢ欲
    -0.06
    irin
    -0.06
    个人è§ĤçĤ¹
    -0.06
    POSITIVE LOGITS
    æīĭä¸ŃçļĦ
    0.08
    çĤ¹èĩ³
    0.08
    ç»ıçĶ±
    0.08
     biais
    0.08
    verso
    0.08
    æĥ
    0.08
     vÃŃa
    0.08
    ÑĩÑĮ
    0.08
    idian
    0.08
    被æĪij
    0.07
    Activations Density 0.159%

    No Known Activations