© 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. 17571
    Prev
    Next
    INDEX
    Explanations

    which

    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
    åĽłä¸ºåħ¶
    -0.10
    çĶ±äºİåħ¶
    -0.09
    mdb
    -0.08
    iful
    -0.08
    åı«ä»ĸ
    -0.08
    ungan
    -0.08
    izon
    -0.08
    è®°
    -0.08
     напÑĢа
    -0.07
    -ish
    -0.07
    POSITIVE LOGITS
    以åıĬ对
    0.09
    èĢĮéĿŀ
    0.09
    以åıĬ
    0.09
    èĢĮä¸įæĺ¯
    0.08
    è¿ĺæľīå°±æĺ¯
    0.08
     rather
    0.08
    åıijçĶŁåľ¨
    0.08
    以åıĬä¸İ
    0.07
     which
    0.07
     resultant
    0.07
    Activations Density 0.192%

    No Known Activations