© 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. 50008
    Prev
    Next
    INDEX
    Explanations

    squaring followed by 2

    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
    alang
    -0.09
    åį«åĨķ
    -0.08
    dol
    -0.07
    almente
    -0.07
    esm
    -0.07
    enes
    -0.07
    ILLS
    -0.07
    iach
    -0.07
    -turned
    -0.07
    å±±ãģ®
    -0.07
    POSITIVE LOGITS
    �
    0.07
    Ħ
    0.07
    èī³
    0.07
    ï¸ı
    0.06
    appy
    0.06
    ifice
    0.06
    ť
    0.06
    ÃŃcula
    0.06
    zial
    0.06
    0.06
    Activations Density 0.015%

    No Known Activations