© 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. 41363
    Prev
    Next
    INDEX
    Explanations

    than

    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
     &$
    -0.24
    积æŀģåıĤä¸İ
    -0.24
    ea
    -0.24
    oine
    -0.24
     treeNode
    -0.23
    utive
    -0.23
    nten
    -0.23
     Feinstein
    -0.23
    onta
    -0.23
     currentTime
    -0.23
    POSITIVE LOGITS
    æİ©çĽĸ
    0.29
    æĮ¤
    0.28
    åºĬåŀ«
    0.26
    æĬľãģij
    0.26
    cratch
    0.25
    èªįèŃĺ
    0.25
    кÑĢ
    0.24
    åĽŀåĪ°å®¶
    0.24
    å¹´æĬ¥
    0.24
    è¯ķçĤ¹å·¥ä½ľ
    0.24
    Activations Density 4.253%

    No Known Activations