© 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. 130176
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    amb
    -0.30
    åŁºè¾ħ
    -0.28
    ÑģÑĤÑĢ
    -0.26
    亦
    -0.25
    UL
    -0.25
    é«ĺä¸Ń
    -0.25
    imited
    -0.24
     cogn
    -0.24
    寡
    -0.24
    adaptive
    -0.24
    POSITIVE LOGITS
    imum
    0.29
    emean
    0.28
    stag
    0.25
     ÄIJảng
    0.25
    eways
    0.24
    éĶµ
    0.24
    REN
    0.24
    LEG
    0.24
    NSBundle
    0.24
     existed
    0.24
    Activations Density 17.055%

    No Known Activations

    This feature has no known activations.