© 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. 130498
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    æĪĸå¤ļ
    -0.28
    ä¸Ģæŀ¶
    -0.27
    SB
    -0.26
    ä½ĵç³»
    -0.26
    亲çĪ±
    -0.26
    ä¸ĢåĪĻ
    -0.25
    åī²
    -0.25
    asil
    -0.24
    ä¿®çIJĨ
    -0.24
     refl
    -0.24
    POSITIVE LOGITS
    pell
    0.26
    åĨ¥
    0.26
    ponents
    0.25
     guessing
    0.24
     bullet
    0.24
    iances
    0.24
    æ»ļçIJĥ
    0.24
     gambling
    0.24
     kissing
    0.24
    泡
    0.23
    Activations Density 1.117%

    No Known Activations