© 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. 41548
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å°¼äºļ
    -0.08
     reluctantly
    -0.06
    è¿Ħ
    -0.06
    çĭł
    -0.06
    zte
    -0.06
    ioned
    -0.06
     nearest
    -0.06
    人家
    -0.06
    iners
    -0.06
    mlin
    -0.06
    POSITIVE LOGITS
    ä¸įåıĹ
    0.08
    kens
    0.08
    aval
    0.08
    mach
    0.08
    bum
    0.08
    _EXTENSION
    0.07
    _EXECUTE
    0.07
    odus
    0.07
    cheon
    0.07
     poroz
    0.07
    Activations Density 0.000%

    No Known Activations