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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6023
    Prev
    Next
    INDEX
    Explanations

    evapor

    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
     ware
    -0.26
     ghost
    -0.26
    -checked
    -0.25
    äºĭ件
    -0.25
    lı
    -0.24
    sWith
    -0.24
     jun
    -0.24
    toMatch
    -0.24
    çĪ¶
    -0.24
    uras
    -0.24
    POSITIVE LOGITS
    åįĥéĩĮ
    0.27
    è¿Ļç¬Ķ
    0.26
    æ°´ä¸Ĭ
    0.26
    çľĭä»ĸ
    0.24
    åijĬè¯īæĪij们
    0.24
    æĥĬå¥ĩ
    0.24
    æĭ¿æĿ¥
    0.24
    rend
    0.24
    æį¢äºĨ
    0.24
    åıįæĺłäºĨ
    0.24
    Activations Density 0.233%

    No Known Activations