© 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. 41495
    Prev
    Next
    INDEX
    Explanations

    names

    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
    æ°ijå¿ĥ
    -0.31
    pole
    -0.26
    cube
    -0.26
    acular
    -0.26
    mgr
    -0.25
    }});↵
    -0.25
    uib
    -0.25
     unloaded
    -0.24
    -pop
    -0.24
    åĽ½æĥħ
    -0.24
    POSITIVE LOGITS
    æĪ®
    0.25
    bef
    0.25
    ament
    0.25
    (.)
    0.25
    éķī
    0.24
    ç®Ĺ
    0.24
     pylint
    0.24
     occupational
    0.23
    èģĮä¸ļæĬĢèĥ½
    0.23
    çĩİ
    0.23
    Activations Density 0.221%

    No Known Activations