© 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. 141541
    Prev
    Next
    INDEX
    Explanations

    Web links and references

    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
    cient
    -0.28
    æĪIJåĬŁçļĦ
    -0.27
    .ids
    -0.26
    她说
    -0.25
     sine
    -0.24
    azole
    -0.24
    preced
    -0.24
    above
    -0.24
    éĴĬ
    -0.24
    pora
    -0.24
    POSITIVE LOGITS
    ARAM
    0.25
    æĹłå¥Ī
    0.24
     vs
    0.24
    èģĶ
    0.24
    ä¸Ģ个éĩįè¦ģ
    0.24
    ä¹ĭäºī
    0.24
    igt
    0.23
    翼
    0.23
    ä¸īåĽ½
    0.23
    äºī
    0.23
    Activations Density 1.873%

    No Known Activations