© 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. 33093
    Prev
    Next
    INDEX
    Explanations

    both, individually, each

    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
    estens
    -0.08
    èģĮåĬ¡
    -0.08
    lt
    -0.08
    à§ĥত
    -0.07
    laud
    -0.07
    ocos
    -0.07
    åIJĮåIJį
    -0.07
    apta
    -0.07
    adhan
    -0.07
    ping
    -0.07
    POSITIVE LOGITS
    éģ¿åħįåĩºçİ°
    0.09
     individually
    0.09
    éĥ½å¿ħé¡»
    0.07
    åĿĩ
    0.07
     independently
    0.07
    ç©Ĺ
    0.07
    ä¹Łéĥ½
    0.07
    亦
    0.07
    è¦ģä¸įçĦ¶
    0.07
    ä¸Ńéĥ½
    0.06
    Activations Density 0.021%

    No Known Activations