© 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. 22-TRANSCODER-HP
    7. 88989
    Prev
    Next
    INDEX
    Explanations

    Personal needs and desires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    nodoc
    -0.24
    osh
    -0.24
    servername
    -0.24
    åºŁè¯Ŀ
    -0.24
     gang
    -0.24
    æĸ°éĹ»åıijå¸ĥ
    -0.24
    phet
    -0.24
    èĨĽ
    -0.23
    èĤĽ
    -0.23
    pras
    -0.23
    POSITIVE LOGITS
    对该
    0.28
    ä¸į对
    0.28
    Ĭ¶
    0.25
    对æѤ
    0.25
    copy
    0.25
    次
    0.25
    .setOn
    0.24
    fly
    0.24
    èģĶ
    0.24
    ä¸Ģ次
    0.23
    Activations Density 0.010%

    No Known Activations