© 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. 162955
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
     Defence
    -0.28
    å¹´ä¸ĭåįĬå¹´
    -0.26
     defence
    -0.26
     Defense
    -0.26
    loud
    -0.25
    gend
    -0.25
    /fa
    -0.25
    å¹´ä¸ĬåįĬå¹´
    -0.25
    é»Ħèī²
    -0.25
    pir
    -0.25
    POSITIVE LOGITS
    åħį
    0.29
    æ¯ĭ
    0.28
    (nullptr
    0.27
    篦
    0.27
    го
    0.26
    åĪĪ
    0.25
    éĻ©
    0.25
    èĢĮåİ»
    0.25
    æݨèįIJéĺħ读
    0.24
     while
    0.24
    Activations Density 0.001%

    No Known Activations