© 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. 141866
    Prev
    Next
    INDEX
    Explanations

    Identification numbers

    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
     joint
    -0.29
    缶
    -0.27
    è´±
    -0.27
    ghan
    -0.26
     ann
    -0.26
    //{{
    -0.25
    èĩªå¾ĭ
    -0.25
    æĮĽ
    -0.25
    é¦
    -0.25
     little
    -0.25
    POSITIVE LOGITS
    åĴĮ个人
    0.28
    éĻª
    0.26
    纪å§Ķ书记
    0.26
    CursorPosition
    0.25
     Drill
    0.24
    .sig
    0.24
     Consultants
    0.23
     Goods
    0.23
    çĶµè§Ĩåı°
    0.23
    å¡«åĨĻ
    0.23
    Activations Density 4.885%

    No Known Activations