© 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. 33094
    Prev
    Next
    INDEX
    Explanations

    here is the

    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
    åĩºãģĹ
    -0.08
    noop
    -0.08
    并å¤Ħ
    -0.07
    ëĥħ
    -0.07
    ago
    -0.07
    asso
    -0.07
    åı¯æ¢¦
    -0.07
    .appspot
    -0.07
    Bootstrap
    -0.07
    dong
    -0.07
    POSITIVE LOGITS
    èĴĻ
    0.08
    çħĮ
    0.07
    bish
    0.06
    erno
    0.06
    ssen
    0.06
    erguson
    0.06
     HOWEVER
    0.06
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    0.06
    æ²³çķĶ
    0.06
    对äºİè¿Ļ个
    0.06
    Activations Density 0.026%

    No Known Activations