© 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. 140962
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    æįĨ
    -0.28
    conf
    -0.28
    çĸ²
    -0.27
    mue
    -0.26
    insky
    -0.26
    人群ä¸Ń
    -0.26
    åĩłä¹İæĺ¯
    -0.25
    åĭī强
    -0.25
     begr
    -0.25
     Transcript
    -0.24
    POSITIVE LOGITS
    èģĮ
    0.29
     pó
    0.28
    管çIJĨæ°´å¹³
    0.28
     reaches
    0.27
    ooth
    0.26
     matters
    0.25
    èį¼
    0.25
     Reach
    0.25
    utan
    0.24
    çĤ¹æ»´
    0.24
    Activations Density 5.514%

    No Known Activations