© 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. 63075
    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
    ustin
    -0.26
     é
    -0.26
    ’é
    -0.26
    æĶ¶å®ĺ
    -0.25
    esse
    -0.25
    quel
    -0.25
    åıijæĸĩ
    -0.24
     ARG
    -0.24
     den
    -0.24
    åij½ä¸Ń
    -0.24
    POSITIVE LOGITS
    locks
    0.31
    è¿ĻäºĽéĹ®é¢ĺ
    0.27
    åı¯è¾¾
    0.26
    èĹģ
    0.26
    çļĦå¿ĥæĥħ
    0.26
    éŃļ
    0.26
    çļĦæ¯Ķä¾ĭ
    0.25
    slide
    0.25
    æľīå¾Īå¤ļç§į
    0.25
    iosity
    0.25
    Activations Density 1.254%

    No Known Activations

    This feature has no known activations.