© 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. 64271
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
     auc
    -0.25
    ä¹Łåıªèĥ½
    -0.25
    ä»ħä¾Ľ
    -0.25
    ãģĹãģĭ
    -0.25
    orer
    -0.24
    BK
    -0.24
     spending
    -0.24
    çļĦ女åĦ¿
    -0.24
     spend
    -0.23
     Rather
    -0.23
    POSITIVE LOGITS
    åĩºå¤Ħ
    0.33
    éĺ¶
    0.28
    vc
    0.26
    ve
    0.25
    åĩºå±Ģ
    0.24
    ismet
    0.24
    _ve
    0.24
     Lê
    0.24
    ationale
    0.24
    èį¤
    0.24
    Activations Density 15.815%

    No Known Activations