© 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. 9034
    Prev
    Next
    INDEX
    Explanations

    questions about parts or aims

    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
    оÑĢÑĤа
    -0.06
    以ä¸ĭåĩłç§į
    -0.06
    letic
    -0.06
     Cheer
    -0.06
    æĢ§è´«è¡Ģ
    -0.06
    oro
    -0.05
     Fle
    -0.05
    æľ¬æ³ķ
    -0.05
    ãĥ¼ãĥ«
    -0.05
    inite
    -0.05
    POSITIVE LOGITS
    imat
    0.09
    éľĢè¦ģä»Ģä¹Ī
    0.08
    /proto
    0.08
    ERG
    0.08
    /questions
    0.08
    ç´³
    0.08
     numbered
    0.08
    ä»Ķ
    0.08
    PGA
    0.08
    aea
    0.08
    Activations Density 0.010%

    No Known Activations