© 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. 30691
    Prev
    Next
    INDEX
    Explanations

    comparison or versus

    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
    /address
    -0.08
    UNA
    -0.08
    ody
    -0.07
    unki
    -0.07
    è¡Įæµĭ
    -0.07
     (()
    -0.07
    obar
    -0.07
    abo
    -0.07
    KeyType
    -0.07
    ubar
    -0.07
    POSITIVE LOGITS
     vs
    0.15
     versus
    0.15
    vs
    0.13
    对æ¯Ķ
    0.11
     VS
    0.10
    _vs
    0.10
     Vs
    0.09
    VS
    0.09
     comparison
    0.09
     Vers
    0.09
    Activations Density 0.155%

    No Known Activations