© 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. 6156
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     safest
    -0.34
    åı¯éĢļè¿ĩ
    -0.28
    _priority
    -0.26
    riet
    -0.26
    лÑij
    -0.26
    +":
    -0.26
    SAFE
    -0.25
    æĬ¼
    -0.24
     priority
    -0.24
    便åı¯
    -0.24
    POSITIVE LOGITS
    aira
    0.27
    çĤ¹åĩ»æŁ¥çľĭ
    0.26
    è¿Ļåıªæĺ¯
    0.25
    éĿ¡
    0.25
    ç¥ŀç»ıç³»ç»Ł
    0.25
     Granite
    0.25
    eval
    0.24
    tır
    0.24
    çĥĤ
    0.24
     conservatism
    0.24
    Activations Density 0.367%

    No Known Activations