© 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. 31678
    Prev
    Next
    INDEX
    Explanations

    plasma, pituitary, depression, growth factor, nickel

    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·ŁçĿĢ
    -0.07
     Opp
    -0.06
    éĶ
    -0.06
    ä¹Ŀéĩį
    -0.06
    kal
    -0.06
    æ´»çĿĢ
    -0.06
     revolution
    -0.06
     ì§ĵ
    -0.06
    âĤ¬
    -0.06
     inc
    -0.06
    POSITIVE LOGITS
    erci
    0.09
    ungk
    0.09
    çŃīåħ¶ä»ĸ
    0.09
    é¾ĻèĻİ
    0.08
    以åıĬåħ¶ä»ĸ
    0.08
    cop
    0.08
     bijvoorbeeld
    0.08
    åIJ¬åıĸäºĨ
    0.08
    anderen
    0.07
    以ä¸ĭ为
    0.07
    Activations Density 1.280%

    No Known Activations