© 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. 19127
    Prev
    Next
    INDEX
    Explanations

    ray trace line segments radius

    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
     moduleId
    -0.06
    ówno
    -0.06
    obil
    -0.06
    ÑĤей
    -0.06
    é£İéĻ©çĽijæݧ
    -0.06
    æĻºæħ§åŀĭ
    -0.06
     semb
    -0.06
     umiejÄĻt
    -0.06
    å¾·éŁ³
    -0.06
     ÙħØŃر
    -0.06
    POSITIVE LOGITS
    ç©¿
    0.07
    ray
    0.07
     ray
    0.06
    Ray
    0.06
     Ray
    0.06
    0.06
    etu
    0.06
     penetrating
    0.06
    z
    0.06
    ç©¿è¿ĩ
    0.05
    Activations Density 0.005%

    No Known Activations