© 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. 161881
    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
    çĸ¾
    -0.31
    åį§
    -0.30
    ally
    -0.30
    ä¸įæĺĵ
    -0.30
    ç¿ģ
    -0.28
    éģĩ
    -0.27
    åıijè¨Ģ
    -0.27
    éĩĩ访æŶ
    -0.26
     counting
    -0.25
    åºĶèģĺ
    -0.25
    POSITIVE LOGITS
     Riot
    0.27
    <?,
    0.25
    ¡°
    0.25
    vince
    0.24
    tees
    0.24
    eut
    0.23
    éªij士
    0.23
     Slut
    0.23
    ?,?,?,?,
    0.23
    otts
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.