© 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. 30-TRANSCODER-HP
    7. 96786
    Prev
    Next
    INDEX
    Explanations

    legal and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uries
    -0.29
    è¿Ļå¼ł
    -0.27
    大å®ĹåķĨåĵģ
    -0.26
    èį·
    -0.26
    æıIJ
    -0.25
     sweetheart
    -0.24
     Europa
    -0.24
    åIJĪ
    -0.24
    -po
    -0.24
    对ä¸įèµ·
    -0.24
    POSITIVE LOGITS
    ines
    0.28
    croll
    0.27
    Corner
    0.25
    ubs
    0.25
    ine
    0.25
    akk
    0.25
     doGet
    0.24
     schedule
    0.24
    ä½ľé£İ建设
    0.24
    ide
    0.24
    Activations Density 0.102%

    No Known Activations