© 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. 7925
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    elo
    -0.32
    鼶éĥ¨ä»¶
    -0.29
    ä¸į失
    -0.29
    ECTOR
    -0.27
    criptors
    -0.26
    ä¾ĽçĶµåħ¬åı¸
    -0.26
    nbr
    -0.25
     stare
    -0.25
    .binding
    -0.25
     photons
    -0.25
    POSITIVE LOGITS
    软
    0.29
    soft
    0.28
     Soft
    0.28
     Mile
    0.27
     gains
    0.27
    æ¹¾
    0.27
     gain
    0.27
    èIJ¥
    0.26
     soft
    0.26
    Soft
    0.26
    Activations Density 0.000%

    No Known Activations