© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30175
    Prev
    Next
    INDEX
    Explanations

    code placeholders and special characters

    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
    åݦ
    -0.07
    -phase
    -0.07
    è¼
    -0.07
    lic
    -0.07
    çĬ¹å¦Ĥ
    -0.07
    éĺµ
    -0.07
    ä¼¼
    -0.07
    shed
    -0.06
    oler
    -0.06
    atum
    -0.06
    POSITIVE LOGITS
    ilib
    0.08
    corre
    0.08
    å§ĭèĩ³
    0.08
    ä½łçļĦåIJįåŃĹ
    0.07
    好æĸĩ
    0.07
    EGI
    0.07
    åľ¨éĤ£éĩĮ
    0.07
    hiro
    0.07
     fatal
    0.07
    ä¸ĢäºĽéĹ®é¢ĺ
    0.07
    Activations Density 0.008%

    No Known Activations