© 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. 128921
    Prev
    Next
    INDEX
    Explanations

    code

    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
    oxic
    -0.29
    óm
    -0.28
    _tem
    -0.27
     recalled
    -0.26
    inas
    -0.24
     té
    -0.24
    adora
    -0.24
    /Getty
    -0.23
    shaw
    -0.23
    森
    -0.23
    POSITIVE LOGITS
    unch
    0.28
    åı¤èĢģçļĦ
    0.26
    åľ°æĸ¹
    0.25
    太ä¹ħ
    0.24
    charge
    0.24
    åľ¨ä¸Ģ
    0.24
    åı¤èĢģ
    0.24
    crap
    0.23
    ...
    0.23
    詹
    0.23
    Activations Density 0.008%

    No Known Activations