© 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. 42407
    Prev
    Next
    INDEX
    Explanations

    e.g., Hall, ancer, constant, Tools

    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
    issa
    -0.07
    æķĻèĤ²å·¥ä½ľ
    -0.06
    æĸ¹çķ¥
    -0.06
    èĬĻèĵī
    -0.06
    æĸ¯é¡¿
    -0.06
    agar
    -0.06
    åħ¶ä¸İ
    -0.06
    ään
    -0.06
    çģ«çĥ§
    -0.06
    á»ģn
    -0.06
    POSITIVE LOGITS
    .vx
    0.08
    ByExample
    0.08
    åľ¨åĶ®
    0.08
     Cadre
    0.08
     TORT
    0.08
     tráng
    0.08
    edList
    0.07
    viders
    0.07
    ×Ļק
    0.07
    _TODO
    0.07
    Activations Density 0.070%

    No Known Activations