© 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. 16457
    Prev
    Next
    INDEX
    Explanations

    now, then

    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
    !=(
    -0.07
    æİ¥è¿ĩ
    -0.07
    大å®ī
    -0.07
    æĽ´æĸ¹ä¾¿
    -0.06
    åħ·ä½ĵè¦ģæ±Ĥ
    -0.06
    ambia
    -0.06
    hra
    -0.06
    avg
    -0.06
     ple
    -0.06
     fen
    -0.06
    POSITIVE LOGITS
     exhaustive
    0.12
    åĨįæĹł
    0.11
    没æľīåħ¶ä»ĸ
    0.11
    ä»ħæľīçļĦ
    0.10
    ç©·
    0.10
    ä¸įä¼ļåĨį
    0.10
    å°±åıªæľī
    0.10
    å°½ãģı
    0.10
    ä»»ä½ķåħ¶ä»ĸ
    0.10
    没æľīæī¾åĪ°
    0.09
    Activations Density 0.048%

    No Known Activations