© 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. 12-TRANSCODER-HP
    7. 22384
    Prev
    Next
    INDEX
    Explanations

    code/document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赶
    -0.28
     dra
    -0.25
    åĪ¶æĪIJ
    -0.24
    æľ«
    -0.24
    AxisSize
    -0.24
    ä»»ä½ķä¸Ģ个
    -0.24
    azo
    -0.24
    졸
    -0.23
    roid
    -0.23
    lood
    -0.23
    POSITIVE LOGITS
    iano
    0.28
    .sections
    0.27
    utch
    0.27
    bnb
    0.26
    sections
    0.26
    æĪ³
    0.26
    ongan
    0.25
     skeleton
    0.25
    大æĸ¹
    0.25
     diffusion
    0.24
    Activations Density 0.001%

    No Known Activations