© 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. 45235
    Prev
    Next
    INDEX
    Explanations

    numbered steps or instructions

    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
    æĬĵä½ıäºĨ
    -0.07
    queira
    -0.07
    çĶ±æѤ
    -0.07
    çī¹çĤ¹æĺ¯
    -0.07
     adanya
    -0.07
    è¶Ĭèµ°
    -0.06
     breaking
    -0.06
    åĸĬçĿĢ
    -0.06
    åıĪæľī
    -0.06
    umping
    -0.06
    POSITIVE LOGITS
    以ä¸ĭæŃ¥éª¤
    0.09
    çļĦæīĢæľīä½ľåĵģ
    0.08
     securely
    0.08
     yourself
    0.08
    eselect
    0.07
     thoroughly
    0.07
    åĩĨå¤ĩå·¥ä½ľ
    0.07
    è¿Ľè¡Įä¸Ģ次
    0.07
     preferably
    0.07
    ä»Ķç»Ĩéĺħ读
    0.07
    Activations Density 0.022%

    No Known Activations