© 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. 161918
    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
     szczegóÅĤowo
    -0.28
    _Pods
    -0.28
    throp
    -0.27
    -Methods
    -0.27
     Grow
    -0.25
    nst
    -0.25
    ctors
    -0.25
    /Gate
    -0.25
    -touch
    -0.25
    chè
    -0.25
    POSITIVE LOGITS
     momentarily
    0.26
    arena
    0.26
    çĿĢä»ĸ
    0.26
    è¿Ļä¸ĢåĪ»
    0.26
    鹦
    0.25
    usted
    0.25
     articulated
    0.25
     practiced
    0.24
    欸
    0.24
    SEM
    0.24
    Activations Density 0.111%

    No Known Activations

    This feature has no known activations.