© 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. 108328
    Prev
    Next
    INDEX
    Explanations

    Mixed sources/topics

    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
    åı¯è§ĨåĮĸ
    -0.29
    component
    -0.26
    ä½İä½į
    -0.26
    .component
    -0.25
    instr
    -0.25
     cra
    -0.24
    _secondary
    -0.24
    ission
    -0.24
    Transmission
    -0.23
    veis
    -0.23
    POSITIVE LOGITS
    ãģ¦ãĤĤ
    0.26
    ivia
    0.25
    etto
    0.25
    ths
    0.25
    ÙĬÙĤØ©
    0.25
    eing
    0.25
    fre
    0.24
    è¹ī
    0.24
    remium
    0.24
    aud
    0.24
    Activations Density 3.314%

    No Known Activations