© 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. 107665
    Prev
    Next
    INDEX
    Explanations

    technical documentation and user authentication

    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
     Blazers
    -0.27
    åı®
    -0.26
    èļ¤
    -0.26
    åIJĮæŶ
    -0.25
    oller
    -0.25
    åħĭæĭī
    -0.24
    éĶŁ
    -0.24
    æł½
    -0.24
    endir
    -0.24
    rell
    -0.24
    POSITIVE LOGITS
     legality
    0.33
    åIJĪæ³ķ
    0.31
    resh
    0.28
    åIJĪæ³ķæĢ§
    0.28
     legitimacy
    0.28
    éĿŀæ³ķ
    0.27
     legalization
    0.27
    legal
    0.26
     illegal
    0.25
     Illegal
    0.25
    Activations Density 6.302%

    No Known Activations