© 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. 60844
    Prev
    Next
    INDEX
    Explanations

    keep it showing/off/beyond/powered/forever

    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
    åĩĨæŶ
    -0.08
    å°ıæŶåīį
    -0.08
     Apel
    -0.07
    å¿ĥæĢ¥
    -0.07
     urgently
    -0.07
    ä»İæĿ¥ä¸į
    -0.07
    å¿«çĤ¹
    -0.07
    mok
    -0.07
    ä»İæľª
    -0.07
    æĹ¶æľº
    -0.07
    POSITIVE LOGITS
    æ°¸ä¹ħ
    0.18
     permanent
    0.17
     permanently
    0.17
    Permanent
    0.15
    æ°¸ä¹ħæĢ§
    0.15
     Permanent
    0.14
    permanent
    0.14
     dauerhaft
    0.14
     permanence
    0.14
     Perman
    0.14
    Activations Density 0.199%

    No Known Activations