© 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. 23493
    Prev
    Next
    INDEX
    Explanations

    They, this, music, travel, today

    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
    ira
    -0.06
    az
    -0.06
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.06
    am
    -0.06
    q
    -0.06
    1
    -0.06
    Z
    -0.06
    丼æŀĹ
    -0.06
    æĺŁè¾°
    -0.05
    æŃ¤åľ°
    -0.05
    POSITIVE LOGITS
     '",
    0.09
    ikian
    0.08
    ÑĢÑĤÑĥ
    0.08
    ecken
    0.08
    LError
    0.08
    ugel
    0.08
     ?",
    0.08
    ognito
    0.08
    REATE
    0.08
    -refresh
    0.08
    Activations Density 0.090%

    No Known Activations