© 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. 40715
    Prev
    Next
    INDEX
    Explanations

    code, documentation, mixed text

    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
    å¹ķ
    -0.26
    åľ¨è¿ĻéĩĮ
    -0.25
    åĿı
    -0.25
    ÎĶ
    -0.25
    ä¸į满æĦı
    -0.25
    DDR
    -0.24
    DK
    -0.24
    ior
    -0.24
     swims
    -0.23
     viet
    -0.23
    POSITIVE LOGITS
    culo
    0.27
     honors
    0.26
    uenta
    0.26
    åıijå±ķä¸Ń
    0.25
     Charges
    0.25
    åıijå±ķ
    0.24
    æĹłçĸij
    0.24
    etical
    0.24
     honorary
    0.24
     Charge
    0.24
    Activations Density 0.025%

    No Known Activations