© 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. 6355
    Prev
    Next
    INDEX
    Explanations

    :

    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
    æݥ触åĪ°
    -0.30
    iap
    -0.25
    æݥ触
    -0.25
    è½Ń
    -0.24
    _sid
    -0.24
    æ°ijèIJ¥
    -0.24
    HING
    -0.24
    pac
    -0.23
    ç©¿
    -0.23
    åİĨåı²æĢ§
    -0.23
    POSITIVE LOGITS
    è¹²
    0.27
    æĺ¯ä¸Ģ
    0.26
    èĤ¥
    0.25
    伯
    0.24
    6
    0.24
     regions
    0.24
    1
    0.23
    9
    0.23
     part
    0.23
    jen
    0.22
    Activations Density 0.074%

    No Known Activations