© 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. 45476
    Prev
    Next
    INDEX
    Explanations

    software components/files

    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
    -0.08
    ulong
    -0.06
     d
    -0.06
     -
    -0.06
    æĺ¯çĶ±
    -0.06
    éľľ
    -0.06
     prolonged
    -0.06
    é¡·
    -0.06
     Di
    -0.05
    åľ¨è§Ħå®ļæŶéĹ´åĨħ
    -0.05
    POSITIVE LOGITS
    åij½åIJį为
    0.12
    åIJĮåIJį
    0.11
    åij½åIJįçļĦ
    0.10
    åij½åIJį
    0.10
     reusable
    0.10
     named
    0.10
     **:
    0.09
    ambre
    0.09
     berin
    0.09
    åIJįçĤº
    0.09
    Activations Density 2.134%

    No Known Activations