© 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. 19844
    Prev
    Next
    INDEX
    Explanations

    plan, help, simplified, decreasing, devices

    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
     agent
    -0.05
     agents
    -0.05
     Agents
    -0.05
     Agent
    -0.05
    çĤ³
    -0.05
    Agents
    -0.05
    æı
    -0.05
    çŃł
    -0.05
    å·²ç»ıå®Įåħ¨
    -0.04
     attached
    -0.04
    POSITIVE LOGITS
    åIJİèĢħ
    0.07
    iale
    0.06
    iore
    0.06
    对æĪij们
    0.06
    è¿ĻäºĽéĥ½
    0.06
    ÙĩÙħا
    0.06
     latter
    0.06
    asca
    0.06
    uell
    0.06
    对人
    0.06
    Activations Density 0.068%

    No Known Activations