© 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. 161651
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and organizations

    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
    稽
    -0.27
    é¢ĨæĤŁ
    -0.26
    ãģĦãĤīãģ£ãģĹãĤĥ
    -0.25
    èį£å¹¸
    -0.25
    èħĶ
    -0.24
    astery
    -0.24
    æĪ¢
    -0.24
     âĶĤ
    -0.23
    æѤäºĭ
    -0.23
    ä¸įç¡®å®ļæĢ§
    -0.23
    POSITIVE LOGITS
    esi
    0.26
    åħ¨æĸĩ
    0.26
    ycz
    0.25
    æŦ
    0.25
     Established
    0.24
    /container
    0.24
    产ä¸ļç»ĵæŀĦ
    0.24
    ersen
    0.24
    pai
    0.23
     fog
    0.23
    Activations Density 0.001%

    No Known Activations