© 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. 33983
    Prev
    Next
    INDEX
    Explanations

    achievable combinations

    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
    argc
    -0.08
    åĮĸ为
    -0.07
    为äºĨèĥ½
    -0.07
    ảo
    -0.07
    Õ¿
    -0.07
     Sapphire
    -0.07
    çĥĪæĹ¥
    -0.07
    örd
    -0.06
    å¹²åĺĽ
    -0.06
    ång
    -0.06
    POSITIVE LOGITS
    ä»İçİ°åľ¨
    0.08
     spoÅĽród
    0.08
    KG
    0.08
    à¸Īาà¸ģà¸ģาร
    0.07
     posible
    0.07
     combinations
    0.07
    çļĦä¸Ģç¬Ķ
    0.07
    ä»İéĩį
    0.07
     possibile
    0.06
     achievable
    0.06
    Activations Density 0.012%

    No Known Activations