© 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. 41106
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    thr
    -0.30
     Pur
    -0.27
     PUR
    -0.26
    pur
    -0.26
    achinery
    -0.25
    loor
    -0.25
    ernes
    -0.25
    PLICATION
    -0.24
    arf
    -0.24
    croll
    -0.24
    POSITIVE LOGITS
    .Driver
    0.27
     minX
    0.26
    æĸ°æµªå¾®åįļ
    0.26
    åĨįæĿ¥
    0.25
    quential
    0.25
    åıĪ被
    0.24
    çļĦçŁ¥è¯Ĩ
    0.24
    åIJĿ
    0.23
    .oc
    0.23
     analogous
    0.23
    Activations Density 0.052%

    No Known Activations