© 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. 40023
    Prev
    Next
    INDEX
    Explanations

    isotopes

    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
    سر
    -0.06
    ụt
    -0.06
     memcmp
    -0.06
    èĻŀ
    -0.05
    /her
    -0.05
    ,default
    -0.05
    Opera
    -0.05
     malos
    -0.05
    اج
    -0.05
    &E
    -0.05
    POSITIVE LOGITS
    ä¸Ńéĩij
    0.08
    è·¯ç«Ļ
    0.08
    ]-$
    0.08
    izedName
    0.08
    ring
    0.08
    éĩįçĶŁä¹ĭ
    0.07
    è·¯åħ¬äº¤è½¦
    0.07
    arez
    0.07
    }while
    0.07
    uet
    0.07
    Activations Density 0.018%

    No Known Activations