© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    involved in groups

    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
    inado
    -0.08
    arness
    -0.07
     Gund
    -0.07
    /exp
    -0.06
    eeper
    -0.06
    ielt
    -0.06
    èħĨ
    -0.06
     hÃłm
    -0.06
    è¯ĿæĿ¥
    -0.06
    åľºåIJĪ
    -0.06
    POSITIVE LOGITS
    çĶ¨äºİ
    0.11
     involved
    0.10
    çĶ¨æĿ¥
    0.10
    à¸Ĺีà¹Īà¹ĥà¸Ĭà¹ī
    0.09
     waarop
    0.09
    çĶ¨æĸ¼
    0.09
     подлежа
    0.09
     waarmee
    0.08
    çĶ¨ä»¥
    0.08
     whom
    0.08
    Activations Density 0.388%

    No Known Activations