© 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. 63754
    Prev
    Next
    INDEX
    Explanations

    service, altruism, helping, giving

    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
    æĬķèµĦé£İéĻ©
    -0.07
    aufs
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
     ÑĢазвод
    -0.07
    inders
    -0.06
    æĸĩåĮĸèĩªä¿¡
    -0.06
    åĪ©å®³
    -0.06
    稽
    -0.06
    MetaData
    -0.06
    æĥĬæħĮ
    -0.06
    POSITIVE LOGITS
     altru
    0.11
    使åij½æĦŁ
    0.11
     service
    0.11
    åħ¬çĽĬäºĭä¸ļ
    0.10
    åħ¬çĽĬ
    0.10
    å¥īçĮ®
    0.10
    使åij½
    0.10
     philanth
    0.10
    éĢłç¦ı
    0.10
    æķij人
    0.10
    Activations Density 0.240%

    No Known Activations