© 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. 47130
    Prev
    Next
    INDEX
    Explanations

    relationship and use

    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
     enim
    -0.08
    ä»İèĢĮ
    -0.07
    lamour
    -0.07
     thus
    -0.07
     therefore
    -0.06
    ucci
    -0.06
    --[
    -0.06
     whose
    -0.06
    åħ¶ä½Ļ
    -0.06
    使çĶ¨è¯¥
    -0.06
    POSITIVE LOGITS
     relation
    0.08
    ffect
    0.08
    /how
    0.08
    以åıĬå¦Ĥä½ķ
    0.08
    åħ³ç³»
    0.07
     Relation
    0.07
    åºĦéķĩ
    0.07
     faÈĽÄĥ
    0.07
    æĬĺä¸įæī£
    0.07
    举举
    0.07
    Activations Density 0.160%

    No Known Activations