© 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. 141690
    Prev
    Next
    INDEX
    Explanations

    Giving, selling, offering

    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
    åIJĮæĦı
    -0.37
    åįıåĬ©
    -0.33
    åħģ许
    -0.33
    æıIJä¾Ľ
    -0.33
    çļĦä¿¡ä»»
    -0.32
    çĤ¹åįĬ
    -0.30
    ä¾
    -0.30
     PROVID
    -0.29
    è´¡çĮ®
    -0.29
     authorize
    -0.28
    POSITIVE LOGITS
    elm
    0.28
     concl
    0.27
    emer
    0.25
    [Test
    0.24
    enger
    0.24
    赢家
    0.24
     /.
    0.24
    ÑĢин
    0.23
    è´¬
    0.23
    healthy
    0.23
    Activations Density 19.502%

    No Known Activations