© 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. 20-TRANSCODER-HP
    7. 63210
    Prev
    Next
    INDEX
    Explanations

    cr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĪçIJĨ
    -0.27
    etur
    -0.26
    æĸĩ
    -0.26
    迹
    -0.25
    亿åħĥ
    -0.25
    å·¥ä½ľä¸Ń
    -0.25
    çŃ¾
    -0.24
    hall
    -0.24
    ware
    -0.23
    åijĬè¯īä»ĸ
    -0.23
    POSITIVE LOGITS
    è¶ħè¿ĩäºĨ
    0.28
    æĪİ
    0.25
    пед
    0.25
    overlay
    0.24
     overlay
    0.24
    ç®Ģ便
    0.24
    achat
    0.24
    (:,:,
    0.23
    egree
    0.23
    iw
    0.23
    Activations Density 17.722%

    No Known Activations