© 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. 20-TRANSCODER-HP
    7. 130510
    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_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
    oise
    -0.26
    ose
    -0.24
    :`~
    -0.24
    å¤ļæł·åĮĸ
    -0.23
     behalf
    -0.23
     conform
    -0.23
    .strategy
    -0.23
    ä½ĵçİ°
    -0.23
    @c
    -0.23
    ÂŃi
    -0.23
    POSITIVE LOGITS
    êt
    0.26
    ettle
    0.26
    inded
    0.25
    ató
    0.25
    ä¸ĢéĿ¢
    0.24
    äºĮç»´
    0.24
    usch
    0.23
    åİŁåĽłä¹ĭä¸Ģ
    0.23
    讨
    0.23
     nich
    0.23
    Activations Density 15.811%

    No Known Activations