© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53838
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çݩ家æĿ¥è¯´
    -0.31
    èĮ¸
    -0.26
    å¨ĥå¨ĥ
    -0.24
    åħļçļĦé¢Ĩ导
    -0.22
    ä¸ĩ家
    -0.22
    uhan
    -0.22
    çļĦ人æĿ¥è¯´
    -0.21
    ãģĮãĤī
    -0.21
    åijľ
    -0.20
    ¤æĸŃ
    -0.20
    POSITIVE LOGITS
     for
    1.75
    for
    1.53
     длÑı
    1.45
    对äºİ
    1.42
    	for
    1.34
     für
    1.26
    _for
    1.25
    For
    1.20
     untuk
    1.19
     For
    1.16
    Activations Density 0.489%

    No Known Activations