© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16048
    Prev
    Next
    INDEX
    Explanations

    movement through locations and sequences

    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
     Vedi
    -0.08
    ë£Į
    -0.07
    çķ¥
    -0.07
    èĢ¿
    -0.07
    ä¿IJ
    -0.07
    VEC
    -0.06
    eval
    -0.06
    urr
    -0.06
    çī¹å°Ķ
    -0.06
    VERAGE
    -0.06
    POSITIVE LOGITS
    Breadcrumb
    0.08
    estat
    0.08
    ream
    0.07
    elow
    0.07
     excursion
    0.07
    esc
    0.07
    è¾¾æĪIJçļĦ
    0.07
     revisit
    0.07
    åİĨåı²çļĦ
    0.07
     Replay
    0.07
    Activations Density 0.012%

    No Known Activations