© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95793
    Prev
    Next
    INDEX
    Explanations

    computer networks and code

    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
     Wich
    -0.29
    -buffer
    -0.28
    icut
    -0.28
     buffering
    -0.27
    ilib
    -0.27
    åĽłåŃIJ
    -0.26
    anke
    -0.26
    åľ¨ç½ij绾
    -0.26
    erable
    -0.26
    arian
    -0.26
    POSITIVE LOGITS
    hidden
    0.29
    ç»Ħ建
    0.28
    aked
    0.28
    Hidden
    0.28
     hidden
    0.27
    bot
    0.27
    illusion
    0.26
    åĺ¹
    0.26
     unfolded
    0.26
     command
    0.26
    Activations Density 0.883%

    No Known Activations