© 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. 107534
    Prev
    Next
    INDEX
    Explanations

    gust

    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
     Hed
    -0.28
    XObject
    -0.27
    ãĥĥãĥĹ
    -0.26
    åĽ¾åĥı
    -0.25
    ä¼ģä¸ļæıIJä¾Ľ
    -0.25
    Ò£
    -0.24
    /image
    -0.24
    >Show
    -0.24
     meticulously
    -0.24
    atically
    -0.23
    POSITIVE LOGITS
    scal
    0.27
    esc
    0.27
     rad
    0.25
    owski
    0.25
     corner
    0.25
    cho
    0.25
    èĤīä½ĵ
    0.24
     hÆ°
    0.24
    anas
    0.24
    åĦ¿å¥³
    0.24
    Activations Density 1.386%

    No Known Activations