© 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. 28610
    Prev
    Next
    INDEX
    Explanations

    vector or vectors

    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
    æĬĵæĭį
    -0.08
     Erwachsen
    -0.08
    ikov
    -0.08
    éĥ½åIJĪ
    -0.08
    让åijĺå·¥
    -0.07
    spflicht
    -0.07
    orges
    -0.07
     reopen
    -0.07
     inh
    -0.07
    æŃ»äºº
    -0.07
    POSITIVE LOGITS
     vectors
    0.13
    åIJijéĩı
    0.13
     vector
    0.12
    Vector
    0.11
     Vector
    0.10
    Vectors
    0.10
    _VECTOR
    0.10
    vector
    0.10
    -vector
    0.10
     vec
    0.09
    Activations Density 0.028%

    No Known Activations