© 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. 161763
    Prev
    Next
    INDEX
    Explanations

    an

    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
    çŃīæ´»åĬ¨
    -0.28
    çŃīæĥħåĨµ
    -0.28
    çŃīåĬŁèĥ½
    -0.26
    æѤæĸĩ
    -0.26
    ppe
    -0.26
    çŃīåĽłç´ł
    -0.25
    宣
    -0.25
    copies
    -0.25
    ä¸Ģ个éĹ®é¢ĺ
    -0.25
    ä¹ĭåĬ¿
    -0.24
    POSITIVE LOGITS
    ind
    0.25
    arto
    0.25
     Beg
    0.24
    queryString
    0.24
    头
    0.24
     nexus
    0.23
     beg
    0.23
     head
    0.23
     bedside
    0.23
     constellation
    0.23
    Activations Density 0.013%

    No Known Activations