© 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. 142327
    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
    åĩıå°ijäºĨ
    -0.26
    åįķ
    -0.25
    èįIJ
    -0.25
    ิà¸ĩ
    -0.25
    å¾ħéģĩ
    -0.24
    вел
    -0.24
    shiv
    -0.24
    çļĦåı¯èĥ½æĢ§
    -0.23
    ivia
    -0.23
    åIJįèªī
    -0.23
    POSITIVE LOGITS
    ialis
    0.30
    gota
    0.25
    Tiny
    0.24
    åijĬè¯ī大家
    0.24
    Chunk
    0.24
    chunk
    0.23
    ected
    0.23
    建档
    0.23
    .appspot
    0.23
    ystone
    0.23
    Activations Density 3.000%

    No Known Activations