© 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. 141751
    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
    {/
    -0.28
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    -0.27
    å½
    -0.26
     driving
    -0.25
    ara
    -0.25
    éĢ®
    -0.24
    èŀĤ
    -0.24
     Spot
    -0.24
    iffs
    -0.24
     Tip
    -0.24
    POSITIVE LOGITS
     setObject
    0.27
    åijĪçı¾
    0.25
    æī¾åĪ°äºĨ
    0.25
    å¸Ĥãģ®
    0.25
    æľºåĻ¨
    0.25
    _SU
    0.24
    xbd
    0.24
     Baghd
    0.24
    _consts
    0.23
    ãĤīãģı
    0.23
    Activations Density 31.586%

    No Known Activations

    This feature has no known activations.