© 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. 20-TRANSCODER-HP
    7. 64650
    Prev
    Next
    INDEX
    Explanations

    Antivirus/security software

    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
    Negative Logits
    GRESS
    -0.28
    rade
    -0.27
     motiv
    -0.26
    çļĦä¸ĢéĿ¢
    -0.25
     motive
    -0.25
    _Helper
    -0.24
     moot
    -0.24
     motivation
    -0.24
     bagi
    -0.23
    æĸ¹éĿ¢çļĦ
    -0.23
    POSITIVE LOGITS
    esModule
    0.27
    çĶ³è¯·
    0.27
     Eisen
    0.27
    iat
    0.26
    å°Ķ
    0.26
    åı¤ä»Ĭ
    0.25
    æĭĽåķĨ
    0.25
    reb
    0.24
    suspend
    0.24
    ItemClickListener
    0.24
    Activations Density 6.734%

    No Known Activations