© 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. 23376
    Prev
    Next
    INDEX
    Explanations

    ideally situated

    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
    è²Ĥ
    -0.08
     lorem
    -0.08
    orny
    -0.08
    _que
    -0.08
    _REGISTRY
    -0.07
    IDI
    -0.07
    enor
    -0.07
    OSP
    -0.07
    çīĪçļĦ
    -0.07
    æģ¶éŃĶ
    -0.07
    POSITIVE LOGITS
    боÑĢ
    0.07
    çī¹
    0.06
    çĶ¨éĢĶ
    0.06
     ifade
    0.05
    ä¹ĭçĶ¨
    0.05
     Litt
    0.05
    æļĤæŶ
    0.05
     suite
    0.05
    åķĬåķĬ
    0.05
    ·
    0.05
    Activations Density 0.002%

    No Known Activations