© 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. 27-TRANSCODER-HP
    7. 7781
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æ³¥
    -0.28
    社
    -0.28
    mens
    -0.27
    绣çŃ¹
    -0.27
    mdb
    -0.27
    notice
    -0.26
    rel
    -0.25
    MP
    -0.25
    æ´Ľ
    -0.24
     monastery
    -0.24
    POSITIVE LOGITS
    icana
    0.29
     Conditions
    0.26
    clamation
    0.26
    æ²ĺ
    0.26
    endale
    0.26
     Royale
    0.25
    washer
    0.25
    以人æ°ij
    0.24
    æĺ¥èĬĤæľŁéĹ´
    0.24
    /gin
    0.24
    Activations Density 0.991%

    No Known Activations