© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20100
    Prev
    Next
    INDEX
    Explanations

    award recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ħä¸įåı¯å°ijçļĦ
    -0.06
    å¿ħè¦ģçļĦ
    -0.06
    ae
    -0.05
     eventualmente
    -0.05
     ideally
    -0.05
    اÙĪر
    -0.05
    ein
    -0.05
    åĭ¤
    -0.05
    å°½åı¯èĥ½åľ°
    -0.05
    ga
    -0.05
    POSITIVE LOGITS
    aturan
    0.06
    åIJijè®°èĢħ
    0.06
    èĩªæµģ
    0.06
     Acad
    0.06
    çĻ½çº¸
    0.06
    porto
    0.06
     vold
    0.05
    èĹĿ人
    0.05
    åĨ°å±±
    0.05
     mainstream
    0.05
    Activations Density 0.010%

    No Known Activations