© 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. 31-TRANSCODER-HP
    7. 19868
    Prev
    Next
    INDEX
    Explanations

    Hall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çıIJ
    -0.27
    èĢģçĪ·
    -0.26
    称
    -0.26
    pte
    -0.25
    éĤ£ä»½
    -0.25
    室
    -0.25
     unst
    -0.24
    åĨķ
    -0.24
     room
    -0.24
    -metal
    -0.24
    POSITIVE LOGITS
    morgan
    0.31
    ê°IJ
    0.29
    ķĮ
    0.28
    æĹ¢æľī
    0.27
    str
    0.27
    gren
    0.27
     str
    0.26
    çķĮéĿ¢
    0.26
    ngr
    0.26
     fined
    0.25
    Activations Density 0.004%

    No Known Activations