© 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. 205
    Prev
    Next
    INDEX
    Explanations

    dash

    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
    çĤ®
    -0.27
    å®ĥ们
    -0.26
    ãģ¾ãģ¨
    -0.25
    æĪij们ä¸Ģèµ·
    -0.25
    æīĢ以æĪij
    -0.25
    ä¸ĢèĪ¬çļĦ
    -0.24
    ä¸Ģèµ·æĿ¥
    -0.24
    çģ¯ç¬¼
    -0.24
    æĬ¼
    -0.23
    æŁ´
    -0.23
    POSITIVE LOGITS
    ç¢Ľ
    0.25
    avigator
    0.25
    wayne
    0.24
    He
    0.24
    aal
    0.23
    he
    0.23
     «
    0.23
    aN
    0.23
     extrem
    0.23
    	inst
    0.23
    Activations Density 5.424%

    No Known Activations