© 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. 49606
    Prev
    Next
    INDEX
    Explanations

    radiation and emission

    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
    anax
    -0.09
    ä¸Ģå¤ķ
    -0.09
    åĪ¶èį¯æľīéĻIJåħ¬åı¸
    -0.09
    plx
    -0.08
    å°Ķåħĭ
    -0.08
    ascus
    -0.08
     ['#
    -0.08
    è¿ĩç¥ŀ
    -0.08
    DataReader
    -0.08
    å°Ķé¡¿
    -0.08
    POSITIVE LOGITS
     Emit
    0.09
     emission
    0.09
     accelerating
    0.08
    åıijå°Ħ
    0.08
     emitting
    0.08
     cad
    0.07
     radi
    0.07
    .Send
    0.07
    åĬłéĢŁ
    0.07
     acceleration
    0.07
    Activations Density 0.005%

    No Known Activations