© 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. 30582
    Prev
    Next
    INDEX
    Explanations

    asking questions or needing things

    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
    ·¸
    -0.07
    Acc
    -0.07
     insp
    -0.06
    æĪijä¸Ģ个人
    -0.06
    elly
    -0.06
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    éĢĻåĢĭæĻĤåĢĻ
    -0.06
    ACC
    -0.06
    æĹ©çŁ¥éģĵ
    -0.06
    .visual
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵéĹ®é¢ĺ
    0.09
    éĹ®äºĨ
    0.08
    usic
    0.08
    åķı
    0.07
    éĹ®è¿ĩ
    0.07
    ahas
    0.07
    ìĬµ
    0.07
    ebas
    0.07
    ask
    0.07
     ask
    0.07
    Activations Density 0.004%

    No Known Activations