© 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. 94908
    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
    Negative Logits
    è¡Ĺ
    -0.33
    æĥľ
    -0.32
    说æĺİ
    -0.32
    å®īæİĴ
    -0.31
    åĽ¢
    -0.30
    æłĩè®°
    -0.29
    çī¹æ®ĬçļĦ
    -0.29
    çīĩ
    -0.29
    åħ¬åı¸
    -0.28
    座
    -0.28
    POSITIVE LOGITS
    è··
    0.30
    ittest
    0.26
    iting
    0.26
    å»ĭ
    0.26
    éĩĭ
    0.26
    _dimension
    0.26
    ipop
    0.25
    illing
    0.25
    ¡°
    0.25
     sibling
    0.25
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.