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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22728
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erva
    -0.28
     mun
    -0.27
    å·
    -0.27
     motivation
    -0.25
    rolled
    -0.25
    ä¸įçķĻ
    -0.24
    InputGroup
    -0.24
     muc
    -0.23
    çħ
    -0.23
    itech
    -0.23
    POSITIVE LOGITS
    åį¤
    0.29
    Hal
    0.29
    娣
    0.28
    uhan
    0.27
    æľªæĿ¥åıijå±ķ
    0.27
    -placeholder
    0.26
     Hal
    0.26
     hal
    0.26
    ä¸ĢåĪ»
    0.26
    éĺµ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.