© 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. 46935
    Prev
    Next
    INDEX
    Explanations

    certain types of

    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
    çĬ¹å¦Ĥ
    -0.07
    é¾Ļä¹ĭ
    -0.06
     different
    -0.06
    different
    -0.06
    dua
    -0.06
     Different
    -0.06
    å¾ħéģĩ
    -0.06
    æ·±åħ¥åŁºå±Ĥ
    -0.06
    æ¦Ľ
    -0.06
    åıªç®¡
    -0.06
    POSITIVE LOGITS
    以åıĬä¸ĢäºĽ
    0.13
     certain
    0.13
    æŁIJäºĽ
    0.13
     Certain
    0.12
    Certain
    0.12
    ä¸Ģéĥ¨ãģ®
    0.11
     certaines
    0.11
    ertain
    0.10
    æĺ¯ä¸ĢäºĽ
    0.10
     niekt
    0.10
    Activations Density 0.163%

    No Known Activations