© 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. 19954
    Prev
    Next
    INDEX
    Explanations

    is followed by articles or status

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    å¤Ħ以
    -0.07
    ½
    -0.07
    éĩįä¸Ńä¹ĭéĩį
    -0.07
    icker
    -0.07
    æĮģãģ¤
    -0.07
    ¶
    -0.07
     theirs
    -0.07
    ÙĬÙģØ©
    -0.07
    POSITIVE LOGITS
    åı¯å¾ª
    0.10
    没æľīåħ¶ä»ĸ
    0.09
     keinen
    0.09
     plenty
    0.09
     keine
    0.09
    没æľīä¸Ģ个
    0.08
    nt
    0.08
    è¶³å¤ŁçļĦ
    0.08
     поблизоÑģÑĤи
    0.08
     noticeable
    0.08
    Activations Density 0.236%

    No Known Activations