© 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. 107037
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    nek
    -0.26
    æĺ¼å¤ľ
    -0.26
    lation
    -0.25
    terra
    -0.25
    #@
    -0.25
     dez
    -0.24
    anking
    -0.24
    inar
    -0.24
     expulsion
    -0.23
     Harbour
    -0.23
    POSITIVE LOGITS
    çıŀ
    0.26
    解åĨ³æĸ¹æ¡Ī
    0.24
    amat
    0.24
    ä¿¡æģ¯
    0.24
    麻çĥ¦
    0.24
    åįģåĽĽäºĶ
    0.24
    executable
    0.24
    PRE
    0.24
    åĮĹ大
    0.24
    ('{{
    0.23
    Activations Density 37.823%

    No Known Activations