© 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. 18-TRANSCODER-HP
    7. 88667
    Prev
    Next
    INDEX
    Explanations

    numbers, statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸İæŶ
    -0.27
    mel
    -0.27
    iffer
    -0.26
    以åıĬåħ¶ä»ĸ
    -0.23
    è¿ĺåı¯ä»¥
    -0.23
    dit
    -0.23
    Assembler
    -0.23
    acles
    -0.23
    wer
    -0.23
     Pins
    -0.23
    POSITIVE LOGITS
    们
    0.28
    rios
    0.26
    纪
    0.25
     ::=
    0.24
     cabo
    0.23
    راس
    0.23
    ãģ¯ãģĵãģ¡ãĤī
    0.23
    lesia
    0.22
    æıĨ
    0.22
    uciones
    0.22
    Activations Density 88.095%

    No Known Activations