© 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. 4-TRANSCODER-HP
    7. 103
    Prev
    Next
    INDEX
    Explanations

    fashion or clothing style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ¨ä»½
    -0.26
     _$
    -0.25
    ä¸įç¦ģ
    -0.25
    NESS
    -0.25
     bothered
    -0.24
    stdcall
    -0.24
     Underground
    -0.24
     stdin
    -0.24
     Goth
    -0.24
    åŀ£
    -0.24
    POSITIVE LOGITS
    ä¸Ģ身
    0.28
    angles
    0.27
    ä¼łç»Ł
    0.26
    eling
    0.26
    ë°į
    0.26
    ~
    0.26
    æŃª
    0.24
    Traditional
    0.24
     ÑģоÑģ
    0.24
    èIJ¥åħ»
    0.24
    Activations Density 0.017%

    No Known Activations