© 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. 129404
    Prev
    Next
    INDEX
    Explanations

    Describing relationships, mechanisms, processes

    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
    ;o
    -0.25
    å½Ĵå±ŀäºİ
    -0.24
     xamarin
    -0.24
    èĹĿ
    -0.24
     Pier
    -0.24
    åħ±äº§åħļåijĺ
    -0.24
    ModelIndex
    -0.23
    á»ıi
    -0.23
    Mappings
    -0.23
    æĪĽ
    -0.23
    POSITIVE LOGITS
    eye
    0.29
    ä¼ĺåĬ¿
    0.27
    rus
    0.26
    ------↵↵
    0.25
     exported
    0.25
     Barr
    0.24
    -eye
    0.24
     eye
    0.24
     Traits
    0.24
    -conf
    0.23
    Activations Density 15.158%

    No Known Activations