© 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. 107162
    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
     teardown
    -0.28
    åľ¨åľ°ä¸Ĭ
    -0.26
    rys
    -0.26
    rán
    -0.26
    ByKey
    -0.26
     Lind
    -0.25
    éķ°
    -0.25
     WG
    -0.25
     tea
    -0.25
     front
    -0.25
    POSITIVE LOGITS
     MOT
    0.27
    _VIRTUAL
    0.26
    ibraltar
    0.26
    imus
    0.25
     Virtual
    0.25
    vis
    0.25
    _virtual
    0.25
    AIM
    0.25
    omb
    0.24
    MB
    0.24
    Activations Density 37.301%

    No Known Activations

    This feature has no known activations.