© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64516
    Prev
    Next
    INDEX
    Explanations

    Technical specifications or code

    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
    egov
    -0.25
    rary
    -0.25
    ãĤīãģĦ
    -0.25
    ynthesis
    -0.24
    ünü
    -0.24
    anked
    -0.24
    .jet
    -0.24
    rne
    -0.24
    .jwt
    -0.23
    cimal
    -0.23
    POSITIVE LOGITS
    ç½ijåıĭè¯Ħ论
    0.27
    æķıæĦŁ
    0.26
    ä¸Ģäºĭ
    0.25
     fans
    0.25
    è¿ijäºĽå¹´
    0.25
    Trait
    0.24
    ä¸Ģ件äºĭ
    0.24
    è¡Įäºĭ
    0.24
    Sensitive
    0.24
     sensitive
    0.24
    Activations Density 75.711%

    No Known Activations