© 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. 29582
    Prev
    Next
    INDEX
    Explanations

    financial fees and charges

    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
    éĢĤé¾Ħ
    -0.08
    åĢºåĪ¸ä¿¡æģ¯
    -0.08
    æ±Ĥè´Ń
    -0.08
     nhá»Ŀ
    -0.07
    åĢĻéĢī
    -0.07
     Semaphore
    -0.07
    vel
    -0.07
     setengah
    -0.07
    强éĻ©
    -0.07
    Semaphore
    -0.07
    POSITIVE LOGITS
     charges
    0.09
     prél
    0.08
     charge
    0.08
    大å°Ĩ
    0.08
    äºĭåħĪ
    0.08
     upfront
    0.08
    贵宾
    0.08
     hefty
    0.07
     hidden
    0.07
    charg
    0.07
    Activations Density 0.128%

    No Known Activations