© 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. 64471
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
    åį³åı¯
    -0.34
    stants
    -0.32
    åıªéľĢè¦ģ
    -0.31
    å°±èĥ½
    -0.29
    åıªè¦ģä½ł
    -0.29
    å°±è¡ĮäºĨ
    -0.29
    å°±åı¯ä»¥
    -0.29
    åıªè¦ģ
    -0.28
    lia
    -0.28
    å°±åı¯ä»¥äºĨ
    -0.27
    POSITIVE LOGITS
    assin
    0.27
     force
    0.27
    اÙħÙĦ
    0.26
     prematurely
    0.26
     many
    0.26
     multiple
    0.25
    Č
    0.25
    clud
    0.24
     premature
    0.24
    ophon
    0.24
    Activations Density 18.118%

    No Known Activations