© 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. 18-TRANSCODER-HP
    7. 90248
    Prev
    Next
    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    inium
    -0.32
    æĸ·
    -0.28
    è¾ľè´Ł
    -0.26
     discontin
    -0.26
    åĪĩæĸŃ
    -0.25
     disconnected
    -0.25
    妨ç¢į
    -0.25
    æĸŃ
    -0.24
    wrong
    -0.24
     Disconnect
    -0.24
    POSITIVE LOGITS
    ç´§åĩij
    0.28
    èĿī
    0.26
    otes
    0.26
    obic
    0.25
    åĬ©
    0.25
    èĭ¦
    0.24
    æŃ£åľ¨è¿Ľè¡Į
    0.24
    cimal
    0.24
    åİ»åĵªéĩĮ
    0.24
     revenge
    0.23
    Activations Density 15.127%

    No Known Activations