© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5232
    Prev
    Next
    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢ§å¼º
    -0.34
    _prefs
    -0.26
    achu
    -0.26
    inson
    -0.25
    اخ
    -0.24
    æĬĹçĻĮ
    -0.24
    ç»ĻåŃ©åŃIJ
    -0.24
    æī©
    -0.23
     cheapest
    -0.23
     SIMPLE
    -0.23
    POSITIVE LOGITS
    è¿Ļæł·çļĦè¯Ŀ
    0.27
    INET
    0.26
    plate
    0.26
    LC
    0.26
    plates
    0.25
    ä¸İä¼Ĺ
    0.25
    è·¯ä¸Ĭ
    0.24
    çĭ¬ä¸ĢæĹłäºĮ
    0.24
    Ta
    0.24
    ä¼Ļ
    0.24
    Activations Density 0.271%

    No Known Activations