© 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. 107048
    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
    两ç§į
    -0.28
    éģį
    -0.27
    çIJĨ
    -0.27
    éĥ½æĺ¯éĿŀ常
    -0.26
    æºı
    -0.25
    讲究
    -0.25
    åĢĻéĢī
    -0.25
     Legal
    -0.24
    Legal
    -0.24
    åĶĨ
    -0.24
    POSITIVE LOGITS
    successfully
    0.27
    åĪłéĻ¤æĪIJåĬŁ
    0.26
     Spar
    0.26
    :'/
    0.26
    adays
    0.25
    èŀį为ä¸Ģä½ĵ
    0.25
     Descriptor
    0.25
    geme
    0.24
     successful
    0.24
    æ©Ħ
    0.24
    Activations Density 0.896%

    No Known Activations

    This feature has no known activations.