© 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. 162795
    Prev
    Next
    INDEX
    Explanations

    ether

    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
    _DEFINE
    -0.28
     versa
    -0.26
    PCODE
    -0.26
    FSIZE
    -0.26
    è¿ĻäºĽéĹ®é¢ĺ
    -0.25
     tslint
    -0.25
    immer
    -0.24
    resco
    -0.24
    yles
    -0.24
    é£ŀæī¬
    -0.24
    POSITIVE LOGITS
    äºĨå¤ļå°ij
    0.30
    纳æĸ¯
    0.27
    èIJ¥ä¸ļ
    0.27
     Calling
    0.25
    åĨĻä½ľ
    0.24
    ized
    0.24
    oser
    0.24
    çħ§
    0.23
    osen
    0.23
    ium
    0.23
    Activations Density 0.001%

    No Known Activations