© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62587
    Prev
    Next
    INDEX
    Explanations

    our

    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
    Negative Logits
    为äºĨ让
    -0.27
    çIJĨ解åĴĮ
    -0.27
    åĽºä½ĵ
    -0.27
     اÙĦÙĦÙĬ
    -0.26
    ä¸įåıĺ
    -0.26
    èµŃ
    -0.25
    ä¸įåĬ¨
    -0.25
     padded
    -0.25
     Laure
    -0.24
    wis
    -0.24
    POSITIVE LOGITS
    KÄ°
    0.28
    lee
    0.28
     consider
    0.26
    aten
    0.25
    ervlet
    0.25
    rowser
    0.25
    @a
    0.24
     fear
    0.24
    Touchable
    0.24
    aroo
    0.24
    Activations Density 3.228%

    No Known Activations