© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161794
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭ¿æĿ¥
    -0.31
     Lah
    -0.26
    chema
    -0.23
     Prote
    -0.23
    åĨ²åĬ¨
    -0.23
    .ep
    -0.23
    å¾Ĵ
    -0.23
    èĥľ
    -0.22
    è¨Ģè¯Ń
    -0.22
    ams
    -0.22
    POSITIVE LOGITS
    ulous
    0.32
    BuildContext
    0.30
    #"
    0.27
    溢
    0.26
    rollable
    0.26
     CreateUser
    0.25
    .requires
    0.25
     addCriterion
    0.24
    isNaN
    0.24
    å½¢æĪIJäºĨ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.