© 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. 57857
    Prev
    Next
    INDEX
    Explanations

    question starters

    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
    lickr
    -0.07
    rogen
    -0.06
    åİŁæľ¬çļĦ
    -0.06
    rice
    -0.06
    éĤ®çĶµ
    -0.06
    utti
    -0.06
    çĻ½çº¸
    -0.06
    稽
    -0.06
    aub
    -0.06
    (ro
    -0.06
    POSITIVE LOGITS
    ateur
    0.08
    大马
    0.07
    aih
    0.07
    สà¸ļาย
    0.07
    zee
    0.07
     profund
    0.07
    深度
    0.07
    æ
    0.07
    深度çļĦ
    0.07
    å
    0.07
    Activations Density 0.004%

    No Known Activations