© 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. 141881
    Prev
    Next
    INDEX
    Explanations

    perspectives and viewing

    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
    ä¸į妨
    -0.27
     [{"
    -0.25
    åĩłä½ķ
    -0.25
    IDEO
    -0.24
    _INCLUDED
    -0.24
    å§ĭ
    -0.23
     woke
    -0.23
    Ỿ
    -0.23
    丧
    -0.23
    ä¸Ģéģį
    -0.23
    POSITIVE LOGITS
    bars
    0.25
    樯
    0.25
    åĪ»
    0.25
    ä¹īåĬ¡
    0.25
    XI
    0.24
    주ëĬĶ
    0.24
    ahead
    0.24
    term
    0.24
    urg
    0.23
    èĬĤå¥ı
    0.23
    Activations Density 6.352%

    No Known Activations