© 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. 42276
    Prev
    Next
    INDEX
    Explanations

    scoring goals

    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
    æľį
    -0.07
    人æīĭ
    -0.06
    ç§ī
    -0.06
    æĹ¥ä»¥
    -0.06
    µ¬
    -0.06
     gossip
    -0.06
    ment
    -0.06
    强åĪ¶
    -0.06
    æĶ¶è´¹
    -0.06
     Zeit
    -0.06
    POSITIVE LOGITS
    ãĤĴçĭĻ
    0.08
     scored
    0.08
    -contrib
    0.08
    à¹Ģà¸ļิà¸ģ
    0.08
     streak
    0.08
     scoring
    0.08
    å¾ĹåĪĨ
    0.08
    åľ¨å¹³æŶ
    0.08
     nhắm
    0.08
    target
    0.08
    Activations Density 0.173%

    No Known Activations