© 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. 15758
    Prev
    Next
    INDEX
    Explanations

    repeat or confirm

    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
    OUNTER
    -0.08
    è¡¡
    -0.08
    éģ¨æ¸¸
    -0.08
    anee
    -0.07
    èĢĥèĻijçļĦ
    -0.07
    ç¥ł
    -0.07
    说è¯ĿäºĨ
    -0.07
    erness
    -0.07
    åIJİéģĹçĹĩ
    -0.07
     пеÑĪ
    -0.07
    POSITIVE LOGITS
    ä¸Ģéģį
    0.13
    äºĨä¸Ģéģį
    0.12
    确认
    0.10
    æķ´çIJĨ
    0.09
    確èªį
    0.09
     confirming
    0.08
    confirm
    0.08
     ulang
    0.08
     repeating
    0.08
    åĬłæ·±
    0.08
    Activations Density 0.098%

    No Known Activations