© 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. 24-TRANSCODER-HP
    7. 151233
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    诬
    -0.25
    å¿ħé¡»è¦ģ
    -0.25
    å½¢
    -0.24
    说æĺİ
    -0.24
    ç´łè´¨æķĻèĤ²
    -0.24
    毫æĹł
    -0.24
     nháºŃt
    -0.24
    åĬłçĽĸ
    -0.24
    å¦Ĥæŀľæĺ¯
    -0.23
    ãģªãĤĭ
    -0.23
    POSITIVE LOGITS
    ä¸įå°½
    0.26
    说çļĦè¯Ŀ
    0.25
    strup
    0.25
    ä»Ģä¹Īåij¢
    0.25
    ffer
    0.25
    åľ¨å®¶éĩĮ
    0.25
    ackbar
    0.23
    åľ¨æѤä¹ĭåīį
    0.23
    ort
    0.23
    åľ¨å®¶
    0.23
    Activations Density 0.156%

    No Known Activations