© 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. 51740
    Prev
    Next
    INDEX
    Explanations

    names in text

    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
    ¦
    -0.10
     plag
    -0.07
     semacam
    -0.07
    éľ²å¤©
    -0.07
    ola
    -0.07
    è¿ĺæĺ¯ä¸į
    -0.06
     Banh
    -0.06
     Orr
    -0.06
    :["
    -0.06
     vect
    -0.06
    POSITIVE LOGITS
     eds
    0.09
    æĺ¯åħ¶
    0.08
    иÑĤаÑĢ
    0.08
    /AFP
    0.07
    sampling
    0.07
    aping
    0.07
    PAGE
    0.07
    åĨħæµĭ
    0.07
    ä¸ĢåĬł
    0.07
    ctor
    0.07
    Activations Density 0.106%

    No Known Activations