© 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. 97144
    Prev
    Next
    INDEX
    Explanations

    half

    np_max-act-logits · gemini-2.0-flash
    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
     natural
    -0.30
    ãĤ³ãĥ¼ãĥī
    -0.28
    Natural
    -0.28
    èĩªçĦ¶
    -0.27
     codes
    -0.27
     Natural
    -0.27
    åįĪ
    -0.27
    erate
    -0.26
    onder
    -0.26
     floating
    -0.26
    POSITIVE LOGITS
    å¤©åľ°
    0.27
    æ´
    0.27
    uno
    0.26
    ç½¹
    0.25
    props
    0.25
    忽çĦ¶
    0.25
    skins
    0.24
    quarters
    0.24
    ToOne
    0.24
    LookAndFeel
    0.24
    Activations Density 0.006%

    No Known Activations