© 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. 23505
    Prev
    Next
    INDEX
    Explanations

    ends in -osis or -izer

    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
     appunto
    -0.10
    è¿ĺä¸įå¦Ĥ
    -0.08
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.07
     doch
    -0.07
    éĥ½ä¼ļ
    -0.07
    éĥ½ä¸į太
    -0.07
    éĥ½è§īå¾Ĺ
    -0.07
    éĥ½ä¸įåı¯èĥ½
    -0.07
    éĥ½åĥı
    -0.07
    éĥ½æĺ¯åĽłä¸º
    -0.07
    POSITIVE LOGITS
     meanwhile
    0.19
     inoltre
    0.18
     natomiast
    0.17
     hingegen
    0.17
    åĪĻæĺ¯
    0.17
     however
    0.16
     likewise
    0.16
    åĪĻ
    0.16
    åĪĻ以
    0.16
     же
    0.16
    Activations Density 0.651%

    No Known Activations