© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39618
    Prev
    Next
    INDEX
    Explanations

    well too

    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
    Negative Logits
    æīĵåĵį
    -0.28
     arrives
    -0.28
    .addListener
    -0.26
    æ¯Ķè¾ĥå¤ļ
    -0.26
    ][/
    -0.25
    å¦ĤæĦı
    -0.25
    į°ìĿ´
    -0.25
     >/
    -0.25
     [[]
    -0.24
    illion
    -0.24
    POSITIVE LOGITS
    ä¸ĢåĪĻ
    0.28
     Franco
    0.27
    ndo
    0.27
    entes
    0.26
    ä¸Ģå¼ł
    0.25
    igrant
    0.25
    _TAC
    0.24
    æıIJæĹ©
    0.24
    OAD
    0.24
    ropol
    0.23
    Activations Density 0.403%

    No Known Activations