© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30330
    Prev
    Next
    INDEX
    Explanations

    code/script snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æķĻç»ĥ
    -0.28
    纶
    -0.27
    åIJĦçľģ
    -0.27
    æ¯ıå¹´éĥ½
    -0.26
    ç¶ĵ常
    -0.25
    -alpha
    -0.25
    ControlEvents
    -0.25
    å¼ŁåħĦ
    -0.25
    opup
    -0.25
    æĶ¿
    -0.25
    POSITIVE LOGITS
    åªĴä»ĭ
    0.39
     represent
    0.28
    (MediaType
    0.28
     reinterpret
    0.27
    i
    0.27
     form
    0.26
     context
    0.26
    éĿ¢å¯¹
    0.26
     encompass
    0.26
     Ø
    0.26
    Activations Density 1.611%

    No Known Activations