© 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. 14-TRANSCODER-HP
    7. 41375
    Prev
    Next
    INDEX
    Explanations

    Sizes and dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĹãģ¦ãģĬãģı
    -0.31
    åıįæĺłäºĨ
    -0.27
    è¿Ļæĺ¯ä¸Ģç§į
    -0.26
    åĨįå¤ļ
    -0.25
    iblings
    -0.25
    itters
    -0.24
    ä¸ĢéĹª
    -0.24
    VML
    -0.24
    volt
    -0.23
    æłĩå¿ĹçĿĢ
    -0.23
    POSITIVE LOGITS
    rop
    0.27
     Conse
    0.25
    趣åij³
    0.25
    cest
    0.25
    =S
    0.25
    ot
    0.25
    gew
    0.25
    sim
    0.24
    常
    0.24
     propos
    0.23
    Activations Density 1.778%

    No Known Activations