© 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. 43737
    Prev
    Next
    INDEX
    Explanations

    effect on

    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
    isz
    -0.07
     Äijất
    -0.06
    din
    -0.06
     immediata
    -0.06
    åįĥ亿
    -0.06
    æķijåij½
    -0.06
     nhắm
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    _SETUP
    -0.06
     perennial
    -0.06
    POSITIVE LOGITS
    åĢį
    0.09
    edas
    0.07
    èģļ
    0.07
     factor
    0.07
    rection
    0.07
    ujur
    0.07
    åĽłåŃIJ
    0.07
    åĢįçļĦ
    0.07
    _factor
    0.07
    estia
    0.07
    Activations Density 0.001%

    No Known Activations