© 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. 39425
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    åħħåĪĨçļĦ
    -0.07
    ç¬ĥ
    -0.07
    éĥ¸
    -0.06
    ç»ļ
    -0.06
    adic
    -0.06
    иÑĢо
    -0.06
    d
    -0.06
    alli
    -0.06
    ä¼
    -0.06
    éķ¿èĻ¹
    -0.06
    POSITIVE LOGITS
    .inject
    0.08
    åĿıå¤Ħ
    0.08
    rophe
    0.08
    ður
    0.07
    à§ģষ
    0.07
     Merke
    0.07
     warmly
    0.07
    odos
    0.07
    ÑĢа
    0.07
    WND
    0.07
    Activations Density 0.199%

    No Known Activations