© 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. 130348
    Prev
    Next
    INDEX
    Explanations

    follow

    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
    .TypeOf
    -0.29
    é²ľèĬ±
    -0.27
    ONO
    -0.26
     Directive
    -0.25
    åŃĹåı·
    -0.25
    YC
    -0.25
    å¾Ĺå¤ļ
    -0.25
    .StatusOK
    -0.24
    æĬļæij¸
    -0.24
    ãģĦãĤī
    -0.24
    POSITIVE LOGITS
    iej
    0.31
     oltre
    0.28
    ä½Ļ
    0.27
    bill
    0.26
    .extend
    0.26
    *
    0.26
    (resp
    0.25
    é¦
    0.25
    à¸ģล
    0.25
    -co
    0.24
    Activations Density 0.484%

    No Known Activations