© 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. 88536
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    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
    RefCount
    -0.28
    QDebug
    -0.27
    CSI
    -0.27
    åĵī
    -0.26
     MOZ
    -0.26
    ¤í
    -0.25
    FormsModule
    -0.25
    ensburg
    -0.24
    ~
    -0.24
    ='\
    -0.24
    POSITIVE LOGITS
    dle
    0.26
    ÙĤات
    0.25
    /loader
    0.25
     Tone
    0.25
    ä¹Łåı¯ä»¥
    0.24
    lops
    0.24
     Cant
    0.24
     cant
    0.24
    Ton
    0.23
    (Note
    0.23
    Activations Density 37.028%

    No Known Activations