© 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. 142066
    Prev
    Next
    INDEX
    Explanations

    Desires and intentions

    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
     Germ
    -0.28
     lạc
    -0.28
    æīįè¡Į
    -0.27
    éĩijåĪļ
    -0.26
    å®ŀæĸ½æĸ¹æ¡Ī
    -0.25
    osphere
    -0.25
    èĦ±èIJ½
    -0.25
     aside
    -0.24
    chema
    -0.24
    éģĹ
    -0.24
    POSITIVE LOGITS
    ikit
    0.28
    alu
    0.28
    letter
    0.26
    (letter
    0.25
    çĸļ
    0.25
    空çĻ½
    0.24
    æĦŁåħ´è¶£çļĦ
    0.24
    ifs
    0.24
    è¿ĵ
    0.24
    writer
    0.24
    Activations Density 5.079%

    No Known Activations