© 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. 141057
    Prev
    Next
    INDEX
    Explanations

    code/URLs

    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
    æĽ°
    -0.28
     bound
    -0.26
    Bound
    -0.25
    ä¸Ģå¾ĭ
    -0.24
    æĪı
    -0.24
    åķĨ
    -0.24
    BeginInit
    -0.24
    met
    -0.24
     diá
    -0.23
    An
    -0.23
    POSITIVE LOGITS
    å®Ľ
    0.30
    acus
    0.26
     compr
    0.26
    足
    0.26
    andin
    0.26
    æĭĪ
    0.26
    ocator
    0.24
    illions
    0.24
    æŶéĹ´åĴĮ
    0.24
    abler
    0.24
    Activations Density 8.513%

    No Known Activations