© 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. 64506
    Prev
    Next
    INDEX
    Explanations

    sign up or please view

    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
    è§ģ人
    -0.09
    angkat
    -0.09
    éŀį
    -0.09
    êm
    -0.08
    ừa
    -0.08
    æıIJåĩºè¦ģæ±Ĥ
    -0.08
    براÙĨ
    -0.08
    产æĿĥè¯ģ
    -0.08
    èģĶç³»æĪij
    -0.08
    -0.08
    POSITIVE LOGITS
    False
    0.06
     False
    0.06
     Beckham
    0.05
    çĮľçĮľ
    0.05
    cho
    0.05
    ologist
    0.05
    zek
    0.05
    me
    0.05
    te
    0.05
    É¡
    0.05
    Activations Density 0.012%

    No Known Activations