© 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. 18-TRANSCODER-HP
    7. 90281
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĤ£æ¬¡
    -0.27
    -Ta
    -0.26
    æĹĹ
    -0.25
    å¥ı
    -0.24
    onia
    -0.24
    éģ¿å¼Ģ
    -0.24
    HAV
    -0.24
    声
    -0.23
    æ®ĭ
    -0.23
    renc
    -0.23
    POSITIVE LOGITS
    Inverse
    0.28
    ç´Ĭä¹±
    0.28
    ç¢į
    0.26
    ourt
    0.25
     safely
    0.25
    åIJĦ家
    0.24
    _roll
    0.24
     everyone
    0.24
    _SAFE
    0.24
    VERSE
    0.23
    Activations Density 2.116%

    No Known Activations

    This feature has no known activations.