© 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. 22-TRANSCODER-HP
    7. 97958
    Prev
    Next
    INDEX
    Explanations

    Excerpts from larger texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    模仿
    -0.69
    çĽ¸ä¼¼
    -0.65
     similar
    -0.65
     Similar
    -0.62
     mimic
    -0.62
    Similar
    -0.60
     resemblance
    -0.59
    仿
    -0.59
     mim
    -0.58
    åĢŁéī´
    -0.58
    POSITIVE LOGITS
    æ±Ĺ
    0.28
     brokerage
    0.28
    åde
    0.26
    arning
    0.24
    úa
    0.24
     Tình
    0.24
    æ£ķ
    0.23
    æģ¬
    0.23
    _optional
    0.23
    Éľ
    0.23
    Activations Density 0.002%

    No Known Activations