© 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. 39515
    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
    conscious
    -0.27
    æħİ
    -0.26
    warf
    -0.25
    пÑĢоизвод
    -0.25
    ardin
    -0.25
    ä¸Ģ楼
    -0.24
    æĻ®æĥł
    -0.24
    å¤ĸéĥ¨
    -0.24
    çİĭèĢħ
    -0.24
    singular
    -0.24
    POSITIVE LOGITS
    æĭī
    0.33
    å·
    0.29
    åıĹ
    0.27
    åĬłæ²¹
    0.27
     affected
    0.26
    å¾Ģ
    0.26
    éĥ½ä¸į
    0.25
    _REUSE
    0.25
    pull
    0.25
    æĽ´é«ĺçļĦ
    0.25
    Activations Density 0.430%

    No Known Activations