© 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. 20-TRANSCODER-HP
    7. 141656
    Prev
    Next
    INDEX
    Explanations

    Code/Programming/Problem solving

    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
    Not in Any Lists

    No Comments

    Negative Logits
    atab
    -0.30
     blood
    -0.30
     super
    -0.27
     tun
    -0.27
     tam
    -0.26
    oul
    -0.25
    ccb
    -0.25
    æĸ§
    -0.25
     protected
    -0.25
    bal
    -0.25
    POSITIVE LOGITS
    便æĺ¯
    0.28
    åħ¶å®ĥéĹ®é¢ĺ
    0.27
    éĤ£äºº
    0.27
     ,$
    0.27
    retrieve
    0.25
     Comedy
    0.25
    _rl
    0.25
     zag
    0.24
     comprise
    0.24
    åĬŀ好
    0.24
    Activations Density 47.427%

    No Known Activations