© 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. 49445
    Prev
    Next
    INDEX
    Explanations

    affiliate marketer, bugs, enforcement

    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
    è¦ģæĪij
    -0.08
     appunto
    -0.08
    以åıĬä¸ĢäºĽ
    -0.07
    大家è¦ģ
    -0.07
     theirs
    -0.07
    åºĶäºĪ
    -0.07
    çļĦç¼ĺæķħ
    -0.07
     certain
    -0.07
    çĶļèĩ³æľīäºĽ
    -0.07
     ÙĪØ£ÙĨÙĩ
    -0.07
    POSITIVE LOGITS
     yourself
    0.16
     Yourself
    0.12
     yourselves
    0.12
    äºĨåIJĹ
    0.10
    æĪijåIJ§
    0.10
     accordingly
    0.10
    书åIJ§
    0.09
    åį³åı¯
    0.09
     nhé
    0.09
    åIJ§
    0.09
    Activations Density 0.635%

    No Known Activations