© 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. 63006
    Prev
    Next
    INDEX
    Explanations

    Will not happen again

    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
    æ°¸ä¹ħ
    -0.27
    ox
    -0.27
    Translator
    -0.25
    åĢ©
    -0.25
    erts
    -0.25
    å¡ij
    -0.25
     pen
    -0.24
    olds
    -0.24
     queue
    -0.24
    que
    -0.24
    POSITIVE LOGITS
    å®īåİ¿
    0.27
    糧
    0.27
    çĽħ
    0.25
    ç¼ķ
    0.24
    åħĪè¿ĽæĬĢæľ¯
    0.24
    .exist
    0.24
    éĩįçİ°
    0.23
    .SQLite
    0.23
    åĦĨ
    0.23
     Pist
    0.23
    Activations Density 10.729%

    No Known Activations