© 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. 23-TRANSCODER-HP
    7. 161861
    Prev
    Next
    INDEX
    Explanations

    Increase or decrease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ystick
    -0.27
    uko
    -0.26
    æĦıä¹īä¸ĬçļĦ
    -0.26
    pus
    -0.25
    æĻĤçĤ¹ãģ§
    -0.25
    uppe
    -0.24
    .getDate
    -0.24
    ä¸ªé¡¹çĽ®
    -0.24
    /INFO
    -0.24
    å·¥ä½ľæĢ»ç»ĵ
    -0.24
    POSITIVE LOGITS
    éĢIJå¹´
    0.38
    å°Ĩä¼ļ
    0.37
    ä»ĬåIJİ
    0.37
    æĺİå¹´
    0.37
    å°ĨæĿ¥
    0.37
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.37
    å°Ĩ继ç»Ń
    0.36
     future
    0.36
    æľªæĿ¥
    0.35
    æİ¥ä¸ĭæĿ¥
    0.35
    Activations Density 0.003%

    No Known Activations