© 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. 162033
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    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
    uite
    -0.28
    åīįèĢħ
    -0.27
    åıĮ
    -0.27
     Extend
    -0.26
     Double
    -0.25
    ä¸Ģéĥ¨åĪĨ
    -0.25
    è¿Ļ两个
    -0.25
    uit
    -0.25
    /cc
    -0.24
    åĪĨè£Ĥ
    -0.24
    POSITIVE LOGITS
    ãģĹãĤĩãģĨ
    0.26
    datable
    0.25
     cellular
    0.24
    éĺŁä¼į建设
    0.24
    èĤĩ
    0.24
    çĹķ
    0.24
    åĪĽæĬķ
    0.23
     Rodney
    0.23
     techn
    0.23
     logistical
    0.23
    Activations Density 0.002%

    No Known Activations