© 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. 58524
    Prev
    Next
    INDEX
    Explanations

    html tags and configuration

    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
     incompet
    -0.08
     @}
    -0.07
    ilty
    -0.07
    (Symbol
    -0.07
    StateManager
    -0.07
     "()
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    atem
    -0.07
    çĨŁ
    -0.07
    amus
    -0.07
    POSITIVE LOGITS
    iale
    0.07
     اÙĦتص
    0.07
    ä¸įå¹²
    0.07
     صÙģ
    0.07
    cod
    0.07
    arring
    0.06
    帮åĬ©å¤§å®¶
    0.06
    reb
    0.06
    tp
    0.06
    _UNKNOWN
    0.06
    Activations Density 0.352%

    No Known Activations