© 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. 63648
    Prev
    Next
    INDEX
    Explanations

    Alaska

    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
    quet
    -0.25
    çļĦä¸Ģ项
    -0.25
    qe
    -0.25
     trained
    -0.25
     fil
    -0.24
     FIL
    -0.24
    人为
    -0.24
     RI
    -0.24
    æ±Ĥ
    -0.23
    ÙĤتر
    -0.23
    POSITIVE LOGITS
    ContextHolder
    0.30
    assic
    0.27
    alue
    0.26
     McMahon
    0.25
    ään
    0.24
    åīįä¸ĸ
    0.24
    涯
    0.24
    è£ħå¤ĩåĪ¶éĢł
    0.23
    å·¥åķĨå±Ģ
    0.23
    zelf
    0.23
    Activations Density 2.565%

    No Known Activations