© 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. 30-TRANSCODER-HP
    7. 95253
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è°Ł
    -0.24
    使ä¹ĭ
    -0.24
    ä»İèĢĮ使
    -0.23
    æĦıåIJij
    -0.23
    让人们
    -0.22
    ä¸Ģåij³
    -0.22
    æ°ijæĹıæĸĩåĮĸ
    -0.22
    çĶ¨æĪ·æıIJä¾Ľ
    -0.22
    å¼ĥ
    -0.21
    æĭ¦
    -0.21
    POSITIVE LOGITS
    warts
    0.23
    åĽłæŀľ
    0.23
    çªĹ
    0.23
     ..."↵
    0.21
    erate
    0.20
    onical
    0.20
    unft
    0.20
    ãģ¾ãĤĬ
    0.20
    uters
    0.20
    Ñĥ
    0.20
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.