© 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. 46778
    Prev
    Next
    INDEX
    Explanations

    permanent

    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
    æľīæīĢ
    -0.08
    ael
    -0.07
    çIJ¥
    -0.07
     sanc
    -0.07
    ixa
    -0.07
     Bust
    -0.07
    lever
    -0.07
    rapper
    -0.07
    è·Łè´´
    -0.07
    StateManager
    -0.07
    POSITIVE LOGITS
     permanently
    0.09
    Permanent
    0.08
    æ°¸ä¹ħ
    0.07
    ä¸įæĶ¹
    0.07
     permanent
    0.07
    umo
    0.07
     vĩnh
    0.07
    åħĭæĸ¯
    0.07
    .instance
    0.07
     Permanent
    0.07
    Activations Density 0.589%

    No Known Activations