© 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. 141190
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
    äºĨä¸Ģ
    -0.38
    èµ·æĿ¥
    -0.35
    äºĨ
    -0.34
    ively
    -0.30
    äºĨå¾Īä¹ħ
    -0.29
    keley
    -0.29
    ed
    -0.29
    éģĵ
    -0.28
    äºİ
    -0.28
    äºĨå¤ļå°ij
    -0.28
    POSITIVE LOGITS
    indsight
    0.30
     accru
    0.27
    åħij
    0.26
    éķij
    0.25
    èµĥ
    0.24
    çĸ«
    0.24
    æ¼ıæ°´
    0.24
    ####↵
    0.24
    åħ³åĪĩ
    0.23
    aco
    0.23
    Activations Density 77.299%

    No Known Activations