© 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. 43978
    Prev
    Next
    INDEX
    Explanations

    references

    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
    ledge
    -0.07
    etti
    -0.07
    æīĢè°ĵ
    -0.07
    å½ĵæŶ
    -0.07
    oria
    -0.06
    kow
    -0.06
    ismo
    -0.06
      ↵
    -0.06
    oret
    -0.06
    &
    -0.06
    POSITIVE LOGITS
    uzzer
    0.09
    evas
    0.09
    ":-
    0.09
    evol
    0.09
    Ñħин
    0.08
    ÑĢек
    0.08
    软件ä¸ĭè½½
    0.08
    Ñħан
    0.08
     برابر
    0.08
    åĤ¬äºº
    0.08
    Activations Density 0.004%

    No Known Activations