© 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. 130539
    Prev
    Next
    INDEX
    Explanations

    Scientific / Technical texts

    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
    æ¯Ķçİĩ
    -0.34
     ratio
    -0.31
    çļĦæ¯Ķä¾ĭ
    -0.30
     conferred
    -0.29
    ratio
    -0.29
     percentage
    -0.28
     propor
    -0.28
    çĶŁäº§èĥ½åĬĽ
    -0.27
    èIJ¥ä¸ļé¢Ŀ
    -0.26
     XCT
    -0.26
    POSITIVE LOGITS
    IGH
    0.26
    rig
    0.25
    ilage
    0.25
    TG
    0.25
    ifes
    0.25
    éĶģå®ļ
    0.24
    æ®Ĥ
    0.24
    å±ŀäºİ
    0.24
    SUR
    0.24
    rg
    0.23
    Activations Density 54.674%

    No Known Activations