© 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. 130277
    Prev
    Next
    INDEX
    Explanations

    joined, connected

    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
    çļĦæĸ¹å¼ıæĿ¥
    -0.28
    檬
    -0.26
    LETE
    -0.26
    ül
    -0.26
    (delegate
    -0.25
    ['_
    -0.25
    lke
    -0.24
    æĸ¹å¼ıè¿Ľè¡Į
    -0.24
    æĿĤå¿Ĺ
    -0.23
    亮
    -0.23
    POSITIVE LOGITS
    è§ģ解
    0.28
    å¼Ħ
    0.27
    ç»ĵæŀľ
    0.27
    theid
    0.26
    ạc
    0.25
    çĶ±
    0.24
    fram
    0.24
    .Progress
    0.24
    ks
    0.24
    ään
    0.24
    Activations Density 52.678%

    No Known Activations