© 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. 31909
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    gom
    -0.07
    -hit
    -0.07
    åıĺ为
    -0.07
    archy
    -0.07
    è¿ĺæĺ¯æ²¡æľī
    -0.07
    ablemente
    -0.06
    orph
    -0.06
    ension
    -0.06
    епен
    -0.06
    enzen
    -0.06
    POSITIVE LOGITS
    æĪİ
    0.07
    JT
    0.07
    请éĢīæĭ©
    0.07
    ÑĦлек
    0.07
    åĪĨ享ä¸Ģä¸ĭ
    0.06
    ç¾ļ
    0.06
    wel
    0.06
    yks
    0.06
     âĢ
    0.06
    _bel
    0.06
    Activations Density 0.020%

    No Known Activations