© 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. 162077
    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
     ép
    -0.27
     capture
    -0.26
    cab
    -0.26
    eted
    -0.25
     IR
    -0.24
    颡
    -0.24
    ward
    -0.24
    ewise
    -0.24
     coding
    -0.24
     compression
    -0.24
    POSITIVE LOGITS
    rollers
    0.26
    第ä¸ī次
    0.25
    µ¬
    0.25
    å½»
    0.24
    èĪį
    0.24
    æķĪ
    0.24
    åħ¨å¹´
    0.24
    æݧ
    0.24
    “We
    0.23
    antry
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.