© 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. 12974
    Prev
    Next
    INDEX
    Explanations

    momentum space

    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
    obot
    -0.08
    bare
    -0.07
    ç¯Ļ
    -0.07
    ä¸Ģ女
    -0.07
    ä¸įè¡°
    -0.07
    æĽľ
    -0.06
    enic
    -0.06
    .reload
    -0.06
    åĪºæ¿ĢæĢ§
    -0.06
     bare
    -0.06
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.09
    éal
    0.08
    太å®Ī
    0.07
     tá»įa
    0.07
     âĨĶ
    0.07
    onge
    0.07
     phase
    0.07
     transformed
    0.07
    æĭĽçĶŁä¸ĵä¸ļ
    0.07
    æŀŃ
    0.07
    Activations Density 0.047%

    No Known Activations