© 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. 129501
    Prev
    Next
    INDEX
    Explanations

    computer programs and automation

    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
    éĹ®éģĵ
    -0.30
    æľīä»Ģä¹Ī
    -0.28
    UPLOAD
    -0.25
    uron
    -0.25
    ä¸įéĹ´
    -0.25
    escort
    -0.24
    elong
    -0.24
    tures
    -0.24
    é«ĺæ°´å¹³
    -0.24
     nale
    -0.24
    POSITIVE LOGITS
    æĺıè¿·
    0.27
    çĥĪ
    0.25
    麻çĥ¦
    0.24
    ×ł×¢
    0.24
     Gamb
    0.24
     bows
    0.24
    æĮĩçĶ²
    0.24
     menn
    0.23
    ihan
    0.23
    æłħ
    0.23
    Activations Density 29.525%

    No Known Activations