© 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. 63946
    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
    æľ¬æĬ¥
    -0.39
     retained
    -0.31
    éĶIJ
    -0.28
    æĦı大
    -0.28
     retain
    -0.27
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.27
    retain
    -0.26
    ARAM
    -0.26
    rip
    -0.25
    orient
    -0.25
    POSITIVE LOGITS
    çĺ«
    0.27
    æĭ¯
    0.25
    ÙħاÙĦÙĥ
    0.25
    ibName
    0.25
    tdown
    0.25
    åĬŁè¯¾
    0.25
    æ®ĭéħ·
    0.24
    椿
    0.24
    mph
    0.24
    'an
    0.24
    Activations Density 34.412%

    No Known Activations

    This feature has no known activations.