© 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. 30410
    Prev
    Next
    INDEX
    Explanations

    flow of information/movement

    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
    иона
    -0.28
    osta
    -0.27
    otty
    -0.26
    tile
    -0.25
    ETH
    -0.25
    Instruction
    -0.25
    ×£
    -0.25
    ît
    -0.24
     VO
    -0.24
    ahun
    -0.24
    POSITIVE LOGITS
    ä¸Ģéģį
    0.30
    çĽ¼
    0.27
    æĥ³æī¾
    0.25
    å¾ĢåIJİ
    0.24
    ToUpdate
    0.24
    ä¸ĢæĿ¡é¾Ļ
    0.24
    inel
    0.24
    uco
    0.24
    ä¸ĢéŨ
    0.24
    æĬĬèĩªå·±çļĦ
    0.23
    Activations Density 0.438%

    No Known Activations