© 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. 64199
    Prev
    Next
    INDEX
    Explanations

    religion/spirituality texts

    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
    _BOUND
    -0.25
    ModelAttribute
    -0.25
    .TryParse
    -0.25
    ernen
    -0.24
    à¹Īวà¸Ļ
    -0.24
    à¹īà¸Ļ
    -0.24
    ereo
    -0.24
     hust
    -0.24
    ãģĹãģ¾
    -0.23
     parte
    -0.23
    POSITIVE LOGITS
    è¾¾
    0.30
     Chall
    0.27
    quin
    0.26
    REA
    0.26
    xEB
    0.25
    åı¯è¾¾
    0.25
     Spot
    0.25
    gow
    0.25
    èĥ½è¾¾åĪ°
    0.25
    èį¡
    0.24
    Activations Density 14.226%

    No Known Activations