© 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. 43984
    Prev
    Next
    INDEX
    Explanations

    medical and technical programming

    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
    大æĬĬ
    -0.08
    akup
    -0.07
    ç¬Ļ
    -0.07
     Deniz
    -0.07
    عاÙĨ
    -0.07
    æng
    -0.07
    ä¹ĭç¥ŀ
    -0.07
    uari
    -0.07
    dene
    -0.07
    Ł
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
     hingegen
    0.08
     dagegen
    0.07
     alternatives
    0.07
    ä½ľåĪĻ
    0.06
    åĪĻéľĢè¦ģ
    0.06
     revanche
    0.06
     apalagi
    0.06
    çŃīçī¹æ®Ĭ
    0.06
    åĪĻè¦ģ
    0.06
    Activations Density 0.489%

    No Known Activations