© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    ready, equipped, or in a state of being

    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
     poprzez
    -0.08
    ilon
    -0.07
    åħ¶ä¸ŃåĮħæĭ¬
    -0.07
    ковÑģкий
    -0.07
    åľ¨æѤ
    -0.07
     spoÅĽród
    -0.07
    arium
    -0.07
    uj
    -0.07
     majd
    -0.07
    ls
    -0.07
    POSITIVE LOGITS
     ready
    0.09
    çĬ¶æĢģä¸ĭ
    0.08
    ready
    0.08
    çĬ¶æħĭãģ§
    0.08
    çĬ¶æĢģçļĦ
    0.08
    çļĦçĬ¶æĢģ
    0.08
    满èħĶ
    0.08
    çĬ¶æĢģ
    0.07
    çĿĢåij¢
    0.07
    çĭĢæħĭ
    0.07
    Activations Density 0.486%

    No Known Activations