© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23711
    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
    çķĮ
    -0.29
    adder
    -0.28
    ufen
    -0.26
    lever
    -0.25
     japan
    -0.24
     Mojo
    -0.24
    worth
    -0.24
    交
    -0.23
    ddf
    -0.23
    +y
    -0.23
    POSITIVE LOGITS
    常çĶ¨çļĦ
    0.27
    ä½ļ
    0.26
    Initialization
    0.25
    	Initialize
    0.25
    è¯Ŀ
    0.24
    åĮĸçļĦ
    0.24
    	initialize
    0.24
     til
    0.23
     questions
    0.23
    常è§ģçļĦ
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.