© 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. 16035
    Prev
    Next
    INDEX
    Explanations

    upper triangular structure

    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
    atoria
    -0.08
    .calc
    -0.07
    å®īåħ¨çļĦ
    -0.07
    atorias
    -0.07
    _oauth
    -0.07
     derr
    -0.07
    ÙĤاÛĮ
    -0.07
    _calc
    -0.07
    inium
    -0.07
    [`
    -0.07
    POSITIVE LOGITS
     recognizable
    0.09
    çī¹å¾ģæĺ¯
    0.08
    è¦ģä¹Īæĺ¯
    0.08
    -mod
    0.08
     structure
    0.08
    ç»ĵæŀĦç®Ģåįķ
    0.07
    å¿ħé¡»æĺ¯
    0.07
    çī¹å¾ģ
    0.07
     characteristic
    0.07
    è¦ģä¹Ī
    0.07
    Activations Density 0.014%

    No Known Activations