© 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. 12933
    Prev
    Next
    INDEX
    Explanations

    defining features, distinctive qualities

    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
    anser
    -0.08
    rax
    -0.07
    asil
    -0.07
    çIJĨçļĦ
    -0.07
    ëŀµ
    -0.07
    åı¯è¡ĮæĢ§
    -0.07
    å¿ĥåŃĺ
    -0.07
    æ¶īåıĬ
    -0.07
    umpang
    -0.07
     mơ
    -0.07
    POSITIVE LOGITS
    çī¹å¾ģ
    0.18
    çī¹å¾ģæĺ¯
    0.17
     characteristic
    0.17
    çī¹å¾´
    0.16
     characteristics
    0.16
     distinctive
    0.15
    åĮºåĪ«äºİ
    0.15
    çī¹èī²
    0.15
    çī¹å¾ģçļĦ
    0.15
    çī¹çĤ¹
    0.15
    Activations Density 0.154%

    No Known Activations