© 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
    2. Qwen3-4B
    3. 20-TRANSCODER-HP
    4. 107396
    Prev
    Next
    INDEX
    Explanations

    place or put

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ĥåĬ¨
    -0.27
    ļĮ
    -0.27
    anco
    -0.26
    &action
    -0.25
     resale
    -0.25
    ewnÄĻtr
    -0.24
    åĽ½å®¶æĪĺçķ¥
    -0.23
    /licenses
    -0.23
    ewire
    -0.23
    åĢºåĬ¡
    -0.23
    POSITIVE LOGITS
    éĿĴ
    0.27
    /Area
    0.26
    æĿ¥è®¿
    0.25
    é¦ĸ
    0.25
    ä¸Ģçīĩ
    0.25
    åıĮåıĮ
    0.24
    KT
    0.24
    Num
    0.24
    Periph
    0.24
    _Num
    0.24
    Activations Density 10.279%

    No Known Activations