© 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. 14019
    Prev
    Next
    INDEX
    Explanations

    son of independent

    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
    ç¼Ī
    -0.08
    .rmi
    -0.08
    UTT
    -0.07
    ãĥ£
    -0.07
     parlement
    -0.07
    ç»ļ
    -0.07
    izzo
    -0.07
    ãģªãģĮ
    -0.07
    feof
    -0.07
    éļıåľ°
    -0.07
    POSITIVE LOGITS
    è¿IJåĬ¿
    0.06
    adia
    0.06
     gr
    0.06
    aur
    0.06
     Ham
    0.06
    å®īå¹³
    0.06
    cura
    0.06
     Mits
    0.05
    èį·
    0.05
    engang
    0.05
    Activations Density 0.067%

    No Known Activations